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

    Neuronpedia

    INDEX
    Explanations

    expressions of thanks and acknowledgment

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

    expressing thanks or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.63
     GenerationType
    -0.52
    CppCodeGen
    -0.49
     Paglinawan
    -0.47
     CallOverrides
    -0.47
    pholes
    -0.45
     ProtoMessage
    -0.44
    ^(@
    -0.44
     linkovi
    -0.44
    Personensuche
    -0.43
    POSITIVE LOGITS
     astore
    0.33
    吁
    0.33
     inplace
    0.33
    auto
    0.32
    attare
    0.32
    Reactivity
    0.31
     Ad
    0.31
    outine
    0.31
    amera
    0.31
    ad
    0.30
    Act Density 0.093%

    No Known Activations