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

    Neuronpedia

    INDEX
    Explanations

    Writing/Speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ''.
    -0.07
    )'),↵
    -0.07
    ")},↵
    -0.06
    ="'.
    -0.06
    ै।↵
    -0.06
    "
↵
    -0.06
    "?↵↵
    -0.06
     आन
    -0.06
     %+
    -0.06
    	E
    -0.06
    POSITIVE LOGITS
     Developed
    0.07
     foolish
    0.07
    usal
    0.07
    _ca
    0.07
     Sabbath
    0.06
    barcode
    0.06
    -menu
    0.06
    _CONVERT
    0.06
    الق
    0.06
    -webpack
    0.06
    Act Density 10.961%

    No Known Activations