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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ителем
    -0.07
     tuple
    -0.07
    ombine
    -0.07
    Nib
    -0.07
     lil
    -0.07
     ring
    -0.07
     divisor
    -0.07
     Singleton
    -0.07
    赢
    -0.06
     faker
    -0.06
    POSITIVE LOGITS
    (UINT
    0.07
     chat
    0.07
    acomment
    0.07
    .food
    0.07
     arts
    0.07
     この
    0.07
    htdocs
    0.07
    recipes
    0.06
    益
    0.06
    .website
    0.06
    Act Density 0.031%

    No Known Activations