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

    Neuronpedia

    INDEX
    Explanations

    4chan boards and rapid movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.55
    comes
    0.52
    ure
    0.50
    uk
    0.50
    you
    0.50
    ra
    0.50
     augmenter
    0.50
     wasn
    0.49
     имен
    0.49
    come
    0.48
    POSITIVE LOGITS
    εται
    0.50
    ങ്ങൾ
    0.48
    表格
    0.48
    даг
    0.48
    자
    0.47
    اسي
    0.47
     కలిగి
    0.47
     racked
    0.46
    ㄷ
    0.46
    ড্ডা
    0.45
    Act Density 0.000%

    No Known Activations