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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .template
    -0.06
    .author
    -0.06
    dv
    -0.06
     ineligible
    -0.06
    istrar
    -0.06
    essenger
    -0.06
    pk
    -0.06
    .xyz
    -0.06
    _tx
    -0.06
     load
    -0.06
    POSITIVE LOGITS
    بوب
    0.07
     نس
    0.07
     bitk
    0.07
    _ac
    0.06
    новид
    0.06
    ングル
    0.06
    OperationContract
    0.06
     Marino
    0.06
     그래
    0.06
    iaz
    0.06
    Act Density 0.031%

    No Known Activations