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

    Neuronpedia

    INDEX
    Explanations

    Business descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тепер
    -0.07
    ToEnd
    -0.06
    Stick
    -0.06
     Skinny
    -0.06
     Loved
    -0.06
    SingleNode
    -0.06
    ประจำ
    -0.06
    nun
    -0.06
    оград
    -0.06
     ска
    -0.06
    POSITIVE LOGITS
     Bd
    0.07
    Layer
    0.07
    립니다
    0.07
    (loss
    0.06
    TEL
    0.06
    ."↵↵↵↵
    0.06
     mutant
    0.06
    ारत
    0.06
    =__
    0.06
    _business
    0.06
    Act Density 0.018%

    No Known Activations