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

    Neuronpedia

    INDEX
    Explanations

    function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imulation
    -0.07
     ked
    -0.07
     luxe
    -0.06
    ケース
    -0.06
     rend
    -0.06
     moreover
    -0.06
     κύ
    -0.06
     fot
    -0.06
     запрос
    -0.06
    izing
    -0.06
    POSITIVE LOGITS
    -region
    0.07
    aucoup
    0.07
    assic
    0.07
     prom
    0.06
     гал
    0.06
     …
    0.06
    Tw
    0.06
    vision
    0.06
    ]])↵↵
    0.06
    named
    0.06
    Act Density 0.032%

    No Known Activations