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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individual rights and responsibilities

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

    Confirmation-seeking questions

    np_acts-logits-general · gemini-2.0-flash

    right? yes? huh?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /***/
    -0.52
    SourceChecksum
    -0.49
    </caption>
    -0.49
    ędzie
    -0.45
    lize
    -0.43
    setopt
    -0.43
     Процитовано
    -0.42
    asional
    -0.42
    setHorizontal
    -0.42
    typeorm
    -0.41
    POSITIVE LOGITS
     right
    2.02
    right
    1.69
    Right
    1.60
     Right
    1.59
     huh
    1.57
     isn
    1.56
     RIGHT
    1.44
    RIGHT
    1.39
     aren
    1.35
     correct
    1.33
    Act Density 0.226%

    No Known Activations