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

    Neuronpedia

    INDEX
    Explanations

    Acceptable quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مح
    -0.08
     موجود
    -0.07
     Dul
    -0.07
     iniciar
    -0.07
     подв
    -0.07
     almaktadır
    -0.07
    >());↵
    -0.07
     고객
    -0.06
    Argument
    -0.06
     μετά
    -0.06
    POSITIVE LOGITS
     moderately
    0.07
     moderate
    0.07
    怕
    0.07
     çiz
    0.07
     Quentin
    0.06
    ZA
    0.06
     demonstrated
    0.06
    za
    0.06
    飛
    0.06
     surprisingly
    0.06
    Act Density 0.059%

    No Known Activations