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

    Neuronpedia

    INDEX
    Explanations

    strength

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    итесь
    -0.07
    .Stage
    -0.07
    也开始
    -0.07
    パソ
    -0.07
    ບ
    -0.06
    [ip
    -0.06
     seçen
    -0.06
     sé
    -0.06
     Copp
    -0.06
     valign
    -0.06
    POSITIVE LOGITS
    roy
    0.08
     deficient
    0.07
     rubble
    0.07
    交通枢纽
    0.07
    	tab
    0.07
    >({
    0.07
    brown
    0.07
     Feet
    0.07
    柳州
    0.07
     defeated
    0.06
    Act Density 0.009%

    No Known Activations