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

    Neuronpedia

    INDEX
    Explanations

    end of clause or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.95
    c
    0.60
    ク
    0.58
     आल्सो
    0.57
    ുപ
    0.56
    s
    0.56
     is
    0.55
     অথবা
    0.55
     flexion
    0.55
    isierte
    0.55
    POSITIVE LOGITS
    ون
    0.75
    ığı
    0.62
     кстати
    0.57
    istory
    0.56
     বটে
    0.56
    ၊
    0.55
    다
    0.54
    ja
    0.54
    ình
    0.54
    owe
    0.53
    Act Density 0.005%

    No Known Activations