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

    Neuronpedia

    INDEX
    Explanations

    bit length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    営
    -0.08
    晓
    -0.08
     Obs
    -0.08
    _identifier
    -0.07
     aé
    -0.07
    må
    -0.07
    _floor
    -0.07
    躁
    -0.07
    _point
    -0.07
     locom
    -0.07
    POSITIVE LOGITS
     Security
    0.13
     امنیت
    0.13
     security
    0.12
    Security
    0.12
     keamanan
    0.11
     الأمنية
    0.11
    -security
    0.11
    _SECURITY
    0.10
     bezpieczeń
    0.10
    (Security
    0.10
    Act Density 0.004%

    No Known Activations