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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [msg
    -0.08
    chantment
    -0.07
    鱿
    -0.07
     unconscious
    -0.07
    >${
    -0.07
     CAUSED
    -0.07
    �述
    -0.07
    placing
    -0.07
    麟
    -0.07
    Disconnect
    -0.07
    POSITIVE LOGITS
     (↵↵
    0.08
    &m
    0.07
    瑗
    0.07
    (↵↵
    0.07
    elp
    0.07
     теле
    0.07
    观音
    0.07
    ümüz
    0.07
    “↵↵
    0.07
    _mime
    0.07
    Act Density 0.124%

    No Known Activations