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

    Neuronpedia

    INDEX
    Explanations

    data structure declarations and initializations

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

    Appears in automatically generated code

    np_acts-logits-general · gemini-2.0-flash

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.94
     t
    -0.93
     f
    -0.88
     r
    -0.88
     g
    -0.88
     T
    -0.88
     L
    -0.87
     m
    -0.86
     E
    -0.85
     l
    -0.85
    POSITIVE LOGITS
     myſelf
    1.83
     itſelf
    1.72
     pleaſure
    1.69
     themſelves
    1.56
     purpoſe
    1.54
     ſeveral
    1.54
     houſe
    1.50
     ſtate
    1.50
     ſmall
    1.48
     greateſt
    1.46
    Act Density 0.721%

    No Known Activations