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

    Neuronpedia

    INDEX
    Explanations

    medicine, computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gd
    -0.07
    -de
    -0.07
    =size
    -0.07
     ice
    -0.06
     FI
    -0.06
    icht
    -0.06
     Zus
    -0.06
    	al
    -0.06
    	unit
    -0.06
    :message
    -0.06
    POSITIVE LOGITS
     knowing
    0.08
    Apple
    0.08
     남자
    0.07
    혁
    0.06
     erf
    0.06
    loan
    0.06
     Apple
    0.06
     सन
    0.06
     урок
    0.06
    rapped
    0.06
    Act Density 0.002%

    No Known Activations