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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     分
    -0.09
     covered
    -0.07
     comma
    -0.07
     Marian
    -0.07
     Mac
    -0.06
    (center
    -0.06
     任
    -0.06
     folds
    -0.06
    istribution
    -0.06
     folding
    -0.06
    POSITIVE LOGITS
    addafi
    0.07
    *);↵
    0.07
    Connor
    0.06
    REFERRED
    0.06
     історії
    0.06
    +Sans
    0.06
    as
    0.06
    bestos
    0.06
     شهرهای
    0.06
     às
    0.06
    Act Density 0.005%

    No Known Activations