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

    Neuronpedia

    INDEX
    Explanations

    Shorts memes design cm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     size
    0.40
     stereotypical
    0.40
     metros
    0.38
     因此
    0.37
     метров
    0.37
    ọc
    0.37
     crucifix
    0.37
    两人
    0.36
    org
    0.36
    一些
    0.36
    POSITIVE LOGITS
    }({\
    0.43
    хта
    0.41
    ماية
    0.41
    ventyConfig
    0.40
    일리
    0.39
    تمع
    0.38
    assanam
    0.38
    ейчас
    0.37
    ㇇
    0.37
    ≻
    0.37
    Act Density 0.000%

    No Known Activations