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

    Neuronpedia

    INDEX
    Explanations

    symbols followed by code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    0.69
    ;
    0.68
    :
    0.63
     and
    0.63
    )।
    0.61
    de
    0.60
    ing
    0.60
    ):
    0.59
     can
    0.58
    ),
    0.57
    POSITIVE LOGITS
    ીર
    0.69
    水
    0.68
    其
    0.62
    پرس
    0.61
    その
    0.61
    村
    0.59
    所有
    0.58
    大海
    0.58
    PayPal
    0.57
    主
    0.57
    Act Density 0.233%

    No Known Activations