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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating citation or reference format

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

    introduces lists or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.52
    OGND
    -0.48
     Chwiliwch
    -0.45
    addContainerGap
    -0.44
    Билгалдахарш
    -0.43
    存于互联网档案馆
    -0.42
    clientY
    -0.41
    RTSC
    -0.41
    rungsseite
    -0.41
    RenderAtEndOf
    -0.40
    POSITIVE LOGITS
    usermodel
    0.53
    awtextra
    0.45
    following
    0.44
     defined
    0.43
     following
    0.43
     mian
    0.42
     consisted
    0.40
     برانيه
    0.40
    pula
    0.40
     definido
    0.39
    Act Density 0.379%

    No Known Activations