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

    Neuronpedia

    INDEX
    Explanations

    Fatigue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ורד
    -0.07
     edged
    -0.07
    \xc
    -0.07
     exits
    -0.07
     Höhe
    -0.07
    -0.07
    ﾔ
    -0.06
     savoir
    -0.06
    极致
    -0.06
    谏
    -0.06
    POSITIVE LOGITS
    ㈫
    0.07
    (ms
    0.07
    唪
    0.07
     flaming
    0.07
    +A
    0.07
     fueled
    0.07
     sling
    0.07
    个小时
    0.07
    ⚚
    0.06
     dày
    0.06
    Act Density 0.020%

    No Known Activations