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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     행
    -0.06
     интерес
    -0.06
    ."↵
    -0.06
     εμφ
    -0.06
    .Second
    -0.06
    Anything
    -0.06
    前に
    -0.06
    !"↵↵
    -0.06
    ycin
    -0.06
     Useful
    -0.06
    POSITIVE LOGITS
    ylvania
    0.07
    ώς
    0.07
    ุทร
    0.06
    igne
    0.06
    liness
    0.06
    _exe
    0.06
    ayar
    0.06
    suspend
    0.06
    コード
    0.06
    regnum
    0.06
    Act Density 0.021%

    No Known Activations