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

    Neuronpedia

    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vig
    -0.07
     Ingredient
    -0.06
    作为一名
    -0.06
     hoàng
    -0.06
     Filipino
    -0.06
    shoot
    -0.06
    ۞
    -0.06
    կ
    -0.06
     mate
    -0.06
    trib
    -0.06
    POSITIVE LOGITS
    _typeof
    0.07
     "..
    0.07
    诱
    0.07
    (sequence
    0.06
    whelming
    0.06
    PLICATION
    0.06
    平均水平
    0.06
     reduced
    0.06
     borderline
    0.06
     EQUI
    0.06
    Act Density 0.016%

    No Known Activations