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
     שימוש
    -0.08
     screams
    -0.07
     planned
    -0.07
    部分内容
    -0.07
    -bootstrap
    -0.07
     الكمبيوتر
    -0.07
     مجرد
    -0.07
     Energy
    -0.07
     discouraged
    -0.06
    相伴
    -0.06
    POSITIVE LOGITS
    uliar
    0.07
    omer
    0.07
    PEG
    0.07
    섹
    0.07
    iteral
    0.07
    _table
    0.07
    财产
    0.06
    >
↵
↵
    0.06
    VERAGE
    0.06
    >%
    0.06
    Act Density 0.001%

    No Known Activations