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

    Neuronpedia

    INDEX
    Explanations

    whisky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OR
    -0.07
    or
    -0.07
     卡
    -0.07
     Min
    -0.07
    ilk
    -0.07
     pu
    -0.06
    ALLE
    -0.06
     manipulate
    -0.06
    mult
    -0.06
     pasta
    -0.06
    POSITIVE LOGITS
     ไป
    0.07
     همان
    0.06
     श
    0.06
    Charlie
    0.06
     {?
    0.06
     locker
    0.06
     ipt
    0.06
    Rpc
    0.06
     đoán
    0.06
    Failure
    0.06
    Act Density 0.003%

    No Known Activations