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

    Neuronpedia

    INDEX
    Explanations

    Inspector General

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    궃
    -0.07
     perfectly
    -0.07
     يأتي
    -0.07
     Maybe
    -0.07
     Cemetery
    -0.07
    コーヒー
    -0.07
     Meanwhile
    -0.06
    漩
    -0.06
    졌다
    -0.06
     arbitrarily
    -0.06
    POSITIVE LOGITS
    茅
    0.08
    CTX
    0.07
     readOnly
    0.07
    _write
    0.07
    聘用
    0.07
    CHILD
    0.07
     stmt
    0.07
    PF
    0.06
     pdo
    0.06
    _Input
    0.06
    Act Density 0.012%

    No Known Activations