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

    Neuronpedia

    INDEX
    Explanations

    units and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ़
    0.41
    頊
    0.38
    ತ್ಮ
    0.37
    いただ
    0.37
    addPreferredGap
    0.36
    ंझ
    0.36
    EventListener
    0.36
    victim
    0.36
     nada
    0.35
     azimuthal
    0.35
    POSITIVE LOGITS
    ++;
    0.38
    ций
    0.38
     Из
    0.38
    ными
    0.37
    ened
    0.37
    ukkan
    0.37
    ::*;
    0.36
     корпу
    0.36
     Кор
    0.36
    ствующих
    0.35
    Act Density 0.000%

    No Known Activations