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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    veç
    -0.06
    atis
    -0.06
    Strings
    -0.06
     union
    -0.06
    _slots
    -0.06
     Closet
    -0.06
     дод
    -0.06
     станд
    -0.06
     Vis
    -0.06
    哈
    -0.06
    POSITIVE LOGITS
    valuate
    0.06
    ppelin
    0.06
    .getBoolean
    0.06
     illustrator
    0.06
     uch
    0.06
    	copy
    0.06
     Obr
    0.06
     astrology
    0.06
     sentiment
    0.06
    _WEAPON
    0.06
    Act Density 0.003%

    No Known Activations