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

    Neuronpedia

    INDEX
    Explanations

    CSS style definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dür
    1.62
    i
    1.59
    at
    1.59
    c
    1.54
    на
    1.40
    n
    1.38
    é
    1.36
    k
    1.34
    ان
    1.32
    à
    1.31
    POSITIVE LOGITS
    ...*/
    1.32
     seater
    1.15
    સર
    1.11
     subspace
    1.09
     justify
    1.09
     amusement
    1.09
    StarService
    1.07
     INCIDENTAL
    1.05
     easements
    1.03
     الاساس
    1.03
    Act Density 0.000%

    No Known Activations