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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     composers
    -0.07
    _bit
    -0.07
    Selected
    -0.07
    ")){↵
    -0.07
    남
    -0.06
    ені
    -0.06
    "])↵
    -0.06
    	diff
    -0.06
    reach
    -0.06
    бі
    -0.06
    POSITIVE LOGITS
     asn
    0.07
     الذي
    0.06
    lsx
    0.06
    иту
    0.06
     ／:
    0.06
    房
    0.06
     ilgi
    0.06
     Cardio
    0.05
    вати
    0.05
    //(
    0.05
    Act Density 0.013%

    No Known Activations