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
     firstName
    -0.06
    OSP
    -0.06
     kra
    -0.06
     Sands
    -0.06
     ягод
    -0.05
     Див
    -0.05
     copyrighted
    -0.05
     tuner
    -0.05
    ']);
↵
    -0.05
     parity
    -0.05
    POSITIVE LOGITS
     Http
    0.07
    .exp
    0.07
    _Find
    0.07
    erculosis
    0.06
    clean
    0.06
     '**
    0.06
     Reve
    0.06
    .people
    0.06
     fabrication
    0.06
     Scheme
    0.06
    Act Density 0.048%

    No Known Activations