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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    订单
    -0.06
     使用
    -0.06
     adip
    -0.06
     ازدواج
    -0.06
    zyst
    -0.06
     manifestation
    -0.06
    ysts
    -0.06
     generalized
    -0.06
     BEFORE
    -0.05
     Shift
    -0.05
    POSITIVE LOGITS
    -With
    0.07
    _DIGEST
    0.07
    sí
    0.07
     intertw
    0.07
    resden
    0.07
    _tensor
    0.06
    _banner
    0.06
    .Sequence
    0.06
     jealousy
    0.06
     생각
    0.06
    Act Density 0.038%

    No Known Activations