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

    Neuronpedia

    INDEX
    Explanations

    Scaling data/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profiles
    -0.07
     yake
    -0.07
     טוב
    -0.07
     अच्छा
    -0.07
     nominations
    -0.07
    ात्म
    -0.07
    nne
    -0.07
    ર્મ
    -0.07
     sofern
    -0.07
    	stat
    -0.07
    POSITIVE LOGITS
     масш
    0.10
     преобраз
    0.09
     масштаб
    0.09
    .convert
    0.09
     customization
    0.09
     converting
    0.08
     түр
    0.08
     тыш
    0.08
     conversion
    0.08
     бас
    0.08
    Act Density 0.014%

    No Known Activations