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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "".
    -0.08
    .Combine
    -0.07
    🤚
    -0.07
    ..<
    -0.07
    ピン
    -0.07
    _FAST
    -0.07
    uncated
    -0.07
     AutoMapper
    -0.07
    umbing
    -0.07
    Rpc
    -0.06
    POSITIVE LOGITS
    chron
    0.07
     Transfer
    0.07
    стрел
    0.07
    发放
    0.07
     seam
    0.06
    �
    0.06
    都想
    0.06
    ⬡
    0.06
    拍摄
    0.06
     Phòng
    0.06
    Act Density 0.002%

    No Known Activations