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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ચે
    0.75
    ची
    0.67
    झा
    0.65
    toBottomOf
    0.64
    Frequent
    0.63
     pertains
    0.62
    шаем
    0.62
     calibre
    0.61
     ख्याल
    0.59
     mannitol
    0.59
    POSITIVE LOGITS
    ահ
    0.67
     vezető
    0.65
    घाटन
    0.63
     naked
    0.62
     lon
    0.60
    ovascular
    0.60
    ECUT
    0.59
    0.59
    culus
    0.59
     教育
    0.59
    Act Density 0.001%

    No Known Activations