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

    Neuronpedia

    INDEX
    Explanations

    code comments or documentation sections in programming files

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

    Comments in code (often with copyright)

    np_acts-logits-general · gemini-2.0-flash

    copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.69
    __':
    -0.66
    __":
    -0.59
    </tfoot>
    -0.55
     AppCompat
    -0.54
    InstanceState
    -0.54
    =$?
    -0.53
    findpost
    -0.53
    ArrowToggle
    -0.52
     linkovi
    -0.51
    POSITIVE LOGITS
     *
    0.95
     Савезне
    0.71
     **
    0.60
     *
    0.56
    (*
    0.55
    🔙
    0.55
     *_
    0.53
     stället
    0.52
    [*
    0.52
    **
    0.51
    Act Density 0.091%

    No Known Activations