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

    Neuronpedia

    INDEX
    Explanations

    he followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     होंगी
    0.67
    Have
    0.59
     võivad
    0.55
     ہوسک
    0.53
    స్తున్నాయి
    0.52
     ندار
    0.52
     имеют
    0.51
     הם
    0.51
     می‌کنند
    0.51
    ძლიათ
    0.51
    POSITIVE LOGITS
     himself
    1.16
    eding
    0.77
     was
    0.77
    mming
    0.73
    zek
    0.73
     his
    0.72
    avier
    0.70
     его
    0.68
    aved
    0.68
    aping
    0.63
    Act Density 0.036%

    No Known Activations