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

    Neuronpedia

    INDEX
    Explanations

    references to judges on talent shows

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

    Follows "panel" or start of turn

    np_acts-logits-general · gemini-2.0-flash

    judging panel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.77
    rungsseite
    -0.68
     externi
    -0.62
    Хьажоргаш
    -0.61
     ligiloj
    -0.58
     ComVisible
    -0.56
     pulumi
    -0.55
     Exacts
    -0.55
    UnknownFieldSet
    -0.55
    SharedCtor
    -0.53
    POSITIVE LOGITS
    lorette
    0.39
    transQ
    0.33
     jueces
    0.30
    chsel
    0.28
     singing
    0.28
     pě
    0.28
     läh
    0.28
     zoek
    0.28
    ittä
    0.27
    nextState
    0.27
    Act Density 0.180%

    No Known Activations