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

    Neuronpedia

    INDEX
    Explanations

    lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veya
    0.63
     or
    0.59
    或
    0.55
    或其他
    0.55
     किंवा
    0.55
     или
    0.54
     hoặc
    0.53
     หรือ
    0.52
     või
    0.52
     或
    0.52
    POSITIVE LOGITS
    且
    0.95
    with
    0.92
    とその
    0.91
    并且
    0.90
     disertai
    0.90
    并在
    0.88
    并
    0.88
     ਅਤੇ
    0.85
    並且
    0.84
     with
    0.84
    Act Density 0.464%

    No Known Activations