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

    Neuronpedia

    INDEX
    Explanations

    Path traversal vulnerability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patience
    -0.08
    allo
    -0.08
     habits
    -0.08
     kön
    -0.08
    qua
    -0.08
    allon
    -0.08
     synonym
    -0.08
    씀
    -0.08
     coqu
    -0.07
     Congress
    -0.07
    POSITIVE LOGITS
     Avoid
    0.10
     prevented
    0.10
     securely
    0.10
    Saf
    0.10
     સુર
    0.10
     sanitized
    0.10
     Saf
    0.10
     ಸುರ
    0.10
     নিরাপ
    0.10
     keamanan
    0.10
    Act Density 0.003%

    No Known Activations