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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calibrated
    -0.07
     patriotic
    -0.07
    ?id
    -0.07
     label
    -0.06
     trailers
    -0.06
     Dias
    -0.06
    Id
    -0.06
     sexual
    -0.06
    igated
    -0.06
    (rawValue
    -0.06
    POSITIVE LOGITS
    fty
    0.07
     infinity
    0.07
    _GF
    0.07
    ाइव
    0.06
    getInstance
    0.06
    frau
    0.06
     ningún
    0.06
     potrav
    0.06
     �
    0.06
    ضو
    0.06
    Act Density 0.004%

    No Known Activations