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

    Neuronpedia

    INDEX
    Explanations

    six

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    1.38
    い
    0.96
    ла
    0.95
    ि
    0.94
    ं
    0.82
    ре
    0.82
    া
    0.81
    с
    0.80
    ı
    0.80
    ਾ
    0.78
    POSITIVE LOGITS
    to
    0.83
    Crypto
    0.69
    م
    0.68
    zza
    0.65
    cedores
    0.65
    ku
    0.64
    jší
    0.64
     Кали
    0.64
    zien
    0.63
     أمس
    0.63
    Act Density 0.252%

    No Known Activations