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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getContent
    -0.07
    ㄺ
    -0.07
     количество
    -0.07
    ForeColor
    -0.07
    /')↵
    -0.07
    track
    -0.07
    _MODULES
    -0.06
    PATCH
    -0.06
    (back
    -0.06
     котор
    -0.06
    POSITIVE LOGITS
    yz
    0.08
    orado
    0.08
    rador
    0.07
    udiant
    0.07
    ensa
    0.07
    ㋛
    0.07
    亡
    0.07
    ИН
    0.06
    .eng
    0.06
     forty
    0.06
    Act Density 0.007%

    No Known Activations