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

    Neuronpedia

    INDEX
    Explanations

    terms related to preceding context or prior statements

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

    foregoing followed by reason or conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.58
    ellido
    -0.54
     STS
    -0.54
    Показать
    -0.54
    ellón
    -0.53
    ㎏
    -0.52
    TagMode
    -0.50
    Kalb
    -0.49
    presto
    -0.48
     ProtoMessage
    -0.48
    POSITIVE LOGITS
     Walla
    0.75
     Rus
    0.67
    Walla
    0.60
     getTotal
    0.53
     Helena
    0.50
    DockStyle
    0.49
    LookAnd
    0.48
    Touchable
    0.47
    Rus
    0.47
    Helena
    0.46
    Act Density 0.009%

    No Known Activations