Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or lack of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "understand," "know," "respect," "follow," or "obtain."

    np_acts-logits-general · gemini-2.0-flash

    understand or ask for clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rxjs
    -0.77
    IntoConstraints
    -0.70
    ValueStyle
    -0.63
    ">//
    -0.61
     useStyles
    -0.56
     betweenstory
    -0.56
    السكان
    -0.54
     للمعارف
    -0.53
     belirt
    -0.53
    Itoa
    -0.52
    POSITIVE LOGITS
     understand
    2.96
     understanding
    2.93
     understood
    2.65
     Understanding
    2.58
     understands
    2.57
    understand
    2.56
    understanding
    2.54
     Understand
    2.52
    Understanding
    2.38
    Understand
    2.35
    Act Density 0.462%

    No Known Activations