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

    Neuronpedia

    INDEX
    Explanations

    security compromise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stealth
    0.48
     cryptic
    0.43
     contraband
    0.41
     Criminal
    0.39
     felicit
    0.39
     binh
    0.39
     ladr
    0.39
     verificación
    0.37
     concealment
    0.37
     Stealth
    0.37
    POSITIVE LOGITS
     Wrest
    0.42
     struggles
    0.41
    Wow
    0.39
     compromises
    0.39
     борь
    0.38
    APPLE
    0.38
    重点
    0.37
     deficiencies
    0.37
    ーブ
    0.37
    Telefono
    0.37
    Act Density 0.051%

    No Known Activations