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

    Neuronpedia

    INDEX
    Explanations

    Australia and New Zealand culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.64
    p
    0.63
    h
    0.62
    ah
    0.59
    ata
    0.56
    v
    0.55
    ra
    0.54
    g
    0.54
    z
    0.52
    io
    0.49
    POSITIVE LOGITS
    ᱠ
    0.61
     فلسط
    0.61
     nucleons
    0.60
     вулка
    0.60
     cuchar
    0.59
    рур
    0.58
     líquidos
    0.57
    SCHRAMM
    0.57
     embank
    0.56
     Вул
    0.55
    Act Density 0.001%

    No Known Activations