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

    Neuronpedia

    INDEX
    Explanations

    bookbinding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meines
    0.66
     транс
    0.64
     ফর্ম
    0.64
    >",
    0.64
     філь
    0.64
     nivel
    0.63
     مي
    0.62
     размеры
    0.61
     finanz
    0.61
     página
    0.60
    POSITIVE LOGITS
    다
    0.78
     A
    0.71
     a
    0.67
    वट
    0.66
     U
    0.65
    ain
    0.62
     V
    0.61
    ان
    0.60
     bindings
    0.60
     an
    0.59
    Act Density 0.001%

    No Known Activations