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

    Neuronpedia

    INDEX
    Explanations

    image pixel manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ints
    -0.07
     σ
    -0.06
     x
    -0.06
    	al
    -0.06
     conductor
    -0.06
    сл
    -0.06
    行政
    -0.06
    /*
    -0.06
    All
    -0.06
    seconds
    -0.06
    POSITIVE LOGITS
    -reader
    0.06
    ='{$
    0.06
    했습니다
    0.06
    سك
    0.06
     Mirage
    0.06
     fraught
    0.06
     nedeni
    0.06
     OPC
    0.06
     kể
    0.06
     omas
    0.06
    Act Density 0.054%

    No Known Activations