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

    Neuronpedia

    INDEX
    Explanations

    virus detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अंश
    0.45
    出した
    0.45
    ण्डा
    0.43
    मॉडल
    0.43
    াবদ্ধ
    0.42
    貯
    0.42
    ோவின்
    0.42
     स्रोत
    0.41
    граф
    0.41
    like
    0.41
    POSITIVE LOGITS
    يروس
    0.47
     pinc
    0.46
     kıs
    0.44
     cou
    0.44
     seul
    0.44
     خير
    0.43
    rica
    0.42
     concurso
    0.42
     anuncios
    0.41
     virus
    0.41
    Act Density 0.000%

    No Known Activations