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

    Neuronpedia

    INDEX
    Explanations

    Security vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babae
    -0.09
     beträgt
    -0.08
     prol
    -0.08
     menghasilkan
    -0.08
     Ruth
    -0.08
    筛
    -0.08
    习
    -0.08
     omen
    -0.08
     سور
    -0.08
     സ്ത്രീ
    -0.08
    POSITIVE LOGITS
     VMware
    0.10
     Debian
    0.09
    Apache
    0.09
     Mozilla
    0.08
     mined
    0.08
     semantics
    0.08
    mozilla
    0.08
    Mozilla
    0.08
     działania
    0.08
    Meta
    0.08
    Act Density 0.006%

    No Known Activations