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

    Neuronpedia

    INDEX
    Explanations

    newline characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divorce
    -0.06
     Stop
    -0.06
    Dealer
    -0.06
     incorpor
    -0.06
     Statistical
    -0.06
     divor
    -0.06
    608
    -0.06
     Lord
    -0.06
     uh
    -0.06
    *=*=
    -0.06
    POSITIVE LOGITS
    /(?
    0.06
    верж
    0.06
    AMPL
    0.06
    .properties
    0.06
    Mutation
    0.06
    DIFF
    0.06
    -css
    0.06
     reimbursement
    0.06
    iện
    0.06
     ):↵↵
    0.06
    Act Density 0.002%

    No Known Activations