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

    Neuronpedia

    INDEX
    Explanations

    duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    滘
    -0.07
     Roose
    -0.07
    ժ
    -0.07
    تط
    -0.06
    �
    -0.06
     purpos
    -0.06
    éparation
    -0.06
    兴建
    -0.06
    fdf
    -0.06
    ręcz
    -0.06
    POSITIVE LOGITS
     abnormal
    0.07
    aning
    0.07
    Minimal
    0.07
    며
    0.07
    frei
    0.07
    PLAYER
    0.06
    =>{↵
    0.06
    Anime
    0.06
    refresh
    0.06
    샘
    0.06
    Act Density 0.121%

    No Known Activations