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

    Neuronpedia

    INDEX
    Explanations

    safety, security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Please
    -0.07
    Outside
    -0.07
    surface
    -0.07
    idores
    -0.07
    .IsSuccess
    -0.07
     noktası
    -0.07
    _component
    -0.06
    祝福
    -0.06
     Koh
    -0.06
    谢谢
    -0.06
    POSITIVE LOGITS
    周四
    0.07
     aims
    0.07
     CHAR
    0.07
     السادس
    0.07
    .ss
    0.07
    .sections
    0.06
    (...)
    0.06
     FI
    0.06
    幻
    0.06
    /contact
    0.06
    Act Density 0.026%

    No Known Activations