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

    Neuronpedia

    INDEX
    Explanations

    names of places and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loosely
    1.88
    yre
    1.85
    displaystyle
    1.80
    િ
    1.76
    ğer
    1.75
    GULD
    1.73
    Ảnh
    1.69
     etapas
    1.69
    1.68
     misdemean
    1.68
    POSITIVE LOGITS
    an
    2.23
    سور
    1.83
    م
    1.79
    로
    1.77
    น
    1.76
    是因为
    1.75
    ราว
    1.71
    츈
    1.70
    нэт
    1.69
    ⁄
    1.69
    Act Density 0.064%

    No Known Activations