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

    Neuronpedia

    INDEX
    Explanations

    Costumes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ս
    -0.08
     cathedral
    -0.07
    獨
    -0.07
    第八
    -0.07
    .Th
    -0.07
    HM
    -0.07
    高级
    -0.06
    Clinical
    -0.06
    Circular
    -0.06
     Tiger
    -0.06
    POSITIVE LOGITS
    办好
    0.07
    precio
    0.07
     créd
    0.07
     warns
    0.07
     dismay
    0.07
    _MSK
    0.07
    锞
    0.07
    爱
    0.07
    证监会
    0.07
    (host
    0.07
    Act Density 0.027%

    No Known Activations