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

    Neuronpedia

    INDEX
    Explanations

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     headaches
    1.44
    hand
    1.43
    ے
    1.43
     symptômes
    1.43
    धानी
    1.41
     sullen
    1.41
    Hand
    1.41
     Hand
    1.39
    Have
    1.38
     În
    1.37
    POSITIVE LOGITS
    inerary
    1.41
     mankind
    1.34
    uitar
    1.32
    xavier
    1.31
    nonzero
    1.30
     rains
    1.27
    ̻
    1.26
    ตัน
    1.25
    ્સ
    1.24
    cwnd
    1.24
    Act Density 0.928%

    No Known Activations