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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     projecting
    -0.07
     patches
    -0.07
    以后
    -0.07
    (model
    -0.06
     Federation
    -0.06
    _TRUNC
    -0.06
     barrels
    -0.06
     HIM
    -0.06
    ｯ
    -0.06
     setting
    -0.06
    POSITIVE LOGITS
    mul
    0.06
     bidder
    0.06
    чить
    0.06
    εχ
    0.06
     witch
    0.06
    иров
    0.06
    очки
    0.06
    	continue
    0.06
    ."_
    0.06
     jmp
    0.06
    Act Density 0.013%

    No Known Activations