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

    Neuronpedia

    INDEX
    Explanations

    hand collocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ために
    1.63
    자
    1.48
    ক
    1.46
    in
    1.45
    다
    1.38
    지가
    1.30
     problèmes
    1.25
    на
    1.24
    şağı
    1.23
     راجسټریشن
    1.23
    POSITIVE LOGITS
     (
    2.09
     I
    1.47
    ing
    1.40
    al
    1.27
    n
    1.26
     of
    1.23
     synchron
    1.23
     =
    1.16
    ;
    1.14
    -
    1.11
    Act Density 0.021%

    No Known Activations