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

    Neuronpedia

    INDEX
    Explanations

    file handles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     масс
    -0.10
     трениров
    -0.09
     Lawson
    -0.08
    .mass
    -0.08
     deodor
    -0.08
     rapper
    -0.07
    anyaan
    -0.07
    _mass
    -0.07
    服
    -0.07
     crime
    -0.07
    POSITIVE LOGITS
     എണ്ണം
    0.09
     تعداد
    0.09
     Exhaust
    0.09
    Количество
    0.09
    NUMBER
    0.09
     manic
    0.09
     Anzahl
    0.09
     Número
    0.09
     NUMBER
    0.09
    Número
    0.08
    Act Density 0.005%

    No Known Activations