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

    Neuronpedia

    INDEX
    Explanations

    academic subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棨
    -0.07
    㧐
    -0.07
    ADM
    -0.07
    -)
    -0.07
    蔊
    -0.07
    �
    -0.07
    헿
    -0.06
    �
    -0.06
    _SYMBOL
    -0.06
    	fclose
    -0.06
    POSITIVE LOGITS
     выбрать
    0.08
     Tiffany
    0.08
     gehen
    0.07
    _observer
    0.07
     ליצור
    0.07
     supplemental
    0.07
    Apply
    0.07
     motivational
    0.07
     każdy
    0.07
     ihrer
    0.07
    Act Density 0.079%

    No Known Activations