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

    Neuronpedia

    INDEX
    Explanations

    buffer overflow vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    txt
    0.66
    Y
    0.62
    new
    0.57
    m
    0.57
    b
    0.55
    passed
    0.52
    YA
    0.52
    B
    0.52
     new
    0.51
    link
    0.51
    POSITIVE LOGITS
    гато
    0.63
     piante
    0.62
     variabel
    0.62
    打电话
    0.60
    ēja
    0.59
    anyakan
    0.59
     variabili
    0.59
    齙
    0.58
     pequeno
    0.57
    પે
    0.57
    Act Density 0.021%

    No Known Activations