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

    Neuronpedia

    INDEX
    Explanations

    Foreign language fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Já
    -0.07
    OS
    -0.07
    iros
    -0.07
     anos
    -0.07
    For
    -0.07
    Jos
    -0.07
     aos
    -0.07
     Pais
    -0.06
    ais
    -0.06
    (dispatch
    -0.06
    POSITIVE LOGITS
    only
    0.07
     Known
    0.07
    functions
    0.06
    itored
    0.06
    _people
    0.06
     Female
    0.06
    ılığı
    0.06
    unker
    0.06
     викон
    0.06
    لمات
    0.06
    Act Density 0.043%

    No Known Activations