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

    Neuronpedia

    INDEX
    Explanations

    emotions and states of being related to personal experiences

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

    actions indicating beginnings or endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*@
    -0.35
    pirable
    -0.35
     ан
    -0.34
     bah
    -0.34
     bid
    -0.33
     hama
    -0.33
    不过
    -0.33
    amese
    -0.30
     nim
    -0.30
     TP
    -0.30
    POSITIVE LOGITS
    MLLoader
    0.68
    󠁢
    0.60
    enseignements
    0.59
     propOrder
    0.57
    rrggbb
    0.56
    printStackTrace
    0.54
     MainAxisSize
    0.54
    ✭✭
    0.53
    tangentMode
    0.52
    LookAnd
    0.52
    Act Density 0.053%

    No Known Activations