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

    Neuronpedia

    INDEX
    Explanations

    threaten or threat intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    0.97
    ни
    0.86
    ני
    0.79
    í
    0.73
    েন
    0.71
    ся
    0.70
    чи
    0.70
    ")}
    0.69
    ি
    0.67
    ті
    0.67
    POSITIVE LOGITS
    ’
    1.03
    K
    0.93
    H
    0.84
    র
    0.83
    Ва
    0.80
    D
    0.80
    ل
    0.77
     pals
    0.76
    ća
    0.73
    at
    0.72
    Act Density 0.132%

    No Known Activations