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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أغسط
    -0.08
     bąd
    -0.07
    🧹
    -0.07
    ธนา
    -0.07
     pdu
    -0.07
    回暖
    -0.06
    启示
    -0.06
    误解
    -0.06
    焆
    -0.06
     sæ
    -0.06
    POSITIVE LOGITS
    TEGR
    0.08
     жизни
    0.07
    ancer
    0.07
    _WRAPPER
    0.07
     funeral
    0.07
    ///↵↵
    0.07
    asket
    0.07
    -made
    0.07
    landing
    0.07
    arkin
    0.07
    Act Density 0.002%

    No Known Activations