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

    Neuronpedia

    INDEX
    Explanations

    JSX syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ست
    1.23
    {~
    1.16
    ก็ตาม
    1.16
    $&$-
    1.15
    ></
    1.13
    ?’
    1.13
    މ
    1.13
    ec
    1.08
    没想到
    1.08
     Translational
    1.08
    POSITIVE LOGITS
     וע
    1.40
    ва
    1.27
    ل
    1.23
    ো
    1.22
    ש
    1.15
    ą
    1.14
     получа
    1.12
    нис
    1.12
    на
    1.09
    ość
    1.09
    Act Density 0.001%

    No Known Activations