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

    Neuronpedia

    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Result
    -0.07
    пе
    -0.07
     summed
    -0.07
    土地
    -0.06
     Handling
    -0.06
     близ
    -0.06
     Arabs
    -0.06
     prophet
    -0.06
    Poor
    -0.06
    _alignment
    -0.06
    POSITIVE LOGITS
    apid
    0.07
    _THEME
    0.07
    addAction
    0.07
     السي
    0.06
    อป
    0.06
    ám
    0.06
    辰
    0.06
    -events
    0.06
    _Module
    0.06
    负
    0.06
    Act Density 0.000%

    No Known Activations