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

    Neuronpedia

    INDEX
    Explanations

    references to TV shows and movies

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

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     average
    -0.34
    treat
    -0.32
    verte
    -0.31
    臨
    -0.30
    เว
    -0.29
    天
    -0.29
     vér
    -0.29
    weich
    -0.29
    withdraw
    -0.29
    timos
    -0.29
    POSITIVE LOGITS
    发表于
    0.70
    ModelSerializer
    0.68
    :✨
    0.63
    ConstraintMaker
    0.62
    RTGC
    0.56
     @"/
    0.54
    tagna
    0.53
     ""],
    0.51
    >",
    0.51
    ponses
    0.50
    Act Density 0.068%

    No Known Activations