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

    Neuronpedia

    INDEX
    Explanations

    proselytizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incomes
    -0.06
     sanctuary
    -0.06
     aggrav
    -0.06
     Stat
    -0.06
     chicas
    -0.06
    /false
    -0.06
     dominate
    -0.06
     chica
    -0.06
     Lakers
    -0.06
     Locate
    -0.06
    POSITIVE LOGITS
     затем
    0.07
    .VERSION
    0.07
    syn
    0.06
    gebung
    0.06
    imat
    0.06
    ап
    0.06
    Lista
    0.06
     upside
    0.06
     Fransa
    0.06
    sy
    0.06
    Act Density 0.008%

    No Known Activations