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

    Neuronpedia

    INDEX
    Explanations

    now and then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    να
    1.38
    на
    1.37
    on
    1.32
    ра
    1.23
    но
    1.17
    ко
    1.10
    to
    1.09
    м
    1.09
    ны
    1.09
    ната
    1.07
    POSITIVE LOGITS
    )
    1.57
    ä
    1.38
    3
    1.30
    ing
    1.19
    เป็น
    1.16
    ون
    1.14
    ל
    1.14
    ;
    1.10
    \
    1.09
     and
    1.06
    Act Density 0.000%

    No Known Activations