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

    Neuronpedia

    INDEX
    Explanations

    discussion of topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zodat
    0.54
    s
    0.51
    പടി
    0.50
    ic
    0.49
    0.49
    og
    0.48
     d
    0.47
    ate
    0.47
    éna
    0.47
    ienia
    0.47
    POSITIVE LOGITS
    בו
    0.55
    נה
    0.53
    -
    0.51
     estiver
    0.51
     essences
    0.48
    について
    0.47
    ー
    0.44
     පිළිබඳ
    0.44
     shortages
    0.44
     specifics
    0.43
    Act Density 0.108%

    No Known Activations