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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nep
    -0.07
     heater
    -0.06
     уточ
    -0.06
    _dual
    -0.06
    .Builder
    -0.06
    radouro
    -0.06
     scp
    -0.06
    اصل
    -0.06
    _finalize
    -0.06
    ataset
    -0.06
    POSITIVE LOGITS
    ennie
    0.07
     Reception
    0.07
    aises
    0.07
    年
    0.07
    xico
    0.06
     gathering
    0.06
    Secret
    0.06
     Performance
    0.06
    ذه
    0.06
    CENT
    0.06
    Act Density 0.011%

    No Known Activations