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

    Neuronpedia

    INDEX
    Explanations

    ant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وأشار
    -0.07
    nç
    -0.07
    ủ
    -0.06
     meisjes
    -0.06
     Á
    -0.06
    ás
    -0.06
    <W
    -0.06
    עיתונ
    -0.06
    أتي
    -0.06
    venida
    -0.06
    POSITIVE LOGITS
    딕
    0.07
    jquery
    0.07
    Drawing
    0.07
     Casual
    0.07
    SEQU
    0.07
    практи
    0.07
    ИН
    0.07
     是否
    0.07
    骨头
    0.07
    _seqs
    0.07
    Act Density 0.005%

    No Known Activations