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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masih
    -0.07
    (ix
    -0.07
    ommen
    -0.07
    民間
    -0.07
     Giriş
    -0.06
    いません
    -0.06
     whipped
    -0.06
    ⵜ
    -0.06
    ثقافة
    -0.06
    Inc
    -0.06
    POSITIVE LOGITS
     lowercase
    0.07
    ug
    0.07
    acey
    0.07
    𝑜
    0.07
    其余
    0.07
    typeorm
    0.07
    posite
    0.07
    &W
    0.07
    -length
    0.07
    	static
    0.07
    Act Density 0.016%

    No Known Activations