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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stadium
    -0.08
     chopping
    -0.08
    aught
    -0.07
    �
    -0.07
    eden
    -0.07
    /Main
    -0.07
     competition
    -0.07
     erfahren
    -0.07
     Lov
    -0.07
     adversity
    -0.07
    POSITIVE LOGITS
    Resultados
    0.10
     결과
    0.09
     resultados
    0.09
    void
    0.09
     मूल्य
    0.09
     પરિણામ
    0.09
    aua
    0.09
    Resultado
    0.09
     void
    0.09
     результ
    0.09
    Act Density 0.001%

    No Known Activations