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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apes
    -0.08
     οι
    -0.07
     acciones
    -0.07
     слов
    -0.07
    ぞ
    -0.06
     Any
    -0.06
    lue
    -0.06
     Avenue
    -0.06
    ues
    -0.06
    lep
    -0.06
    POSITIVE LOGITS
    .board
    0.07
     yapmış
    0.07
     하
    0.06
    uming
    0.06
    utenant
    0.06
    'nde
    0.06
    ited
    0.06
    with
    0.06
    .FlatStyle
    0.06
    取得
    0.06
    Act Density 0.058%

    No Known Activations