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

    Neuronpedia

    INDEX
    Explanations

    CSRF/cybersecurity exploits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nc
    -0.07
    _admin
    -0.07
     Goddess
    -0.07
     Associate
    -0.07
     publié
    -0.07
    毁灭
    -0.07
    eward
    -0.07
     mun
    -0.07
    Jam
    -0.07
    ?f
    -0.07
    POSITIVE LOGITS
     daß
    0.07
    较高的
    0.07
    ложение
    0.07
    ocrisy
    0.07
     poids
    0.07
    arLayout
    0.07
    légi
    0.07
     novelty
    0.07
    (level
    0.07
     initWithStyle
    0.07
    Act Density 0.008%

    No Known Activations