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

    Neuronpedia

    INDEX
    Explanations

    legal cases referencing dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     StringUtils
    -0.07
     OU
    -0.07
    Lng
    -0.07
    武汉
    -0.07
    upaten
    -0.07
     institutional
    -0.07
     Laurie
    -0.07
     seins
    -0.07
    MB
    -0.07
    门外
    -0.07
    POSITIVE LOGITS
    �
    0.08
    쎄
    0.07
    せ
    0.07
    珢
    0.07
    _press
    0.07
     Eyl
    0.07
     nesta
    0.07
     реж
    0.06
    recht
    0.06
    恬
    0.06
    Act Density 0.014%

    No Known Activations