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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atomy
    -0.07
    毁灭
    -0.07
    كام
    -0.07
    (transform
    -0.06
    (pm
    -0.06
     qr
    -0.06
    Invalid
    -0.06
     Trigger
    -0.06
    _PREVIEW
    -0.06
    狙击
    -0.06
    POSITIVE LOGITS
    !";
↵
    0.08
    /,↵
    0.08
    湟
    0.07
    /');↵
    0.07
    🥐
    0.07
     alphabetical
    0.07
    有关部门
    0.07
    ]={
    0.07
    /;↵
    0.07
    ChangedEventArgs
    0.07
    Act Density 0.002%

    No Known Activations