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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otle
    -0.07
    (DIR
    -0.07
    CLUSION
    -0.07
    imity
    -0.06
     dilig
    -0.06
    tee
    -0.06
    ߧ
    -0.06
    andas
    -0.06
    dden
    -0.06
    ighet
    -0.06
    POSITIVE LOGITS
    (Menu
    0.07
    _user
    0.07
    .Flat
    0.07
    ?<
    0.07
    河道
    0.07
    .getContentPane
    0.07
    _he
    0.07
     Mason
    0.07
    越
    0.07
     Take
    0.07
    Act Density 0.049%

    No Known Activations