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

    Neuronpedia

    INDEX
    Explanations

    Tyrian, AC, dash, unicursal, Sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.85
    who
    0.99
     coolant
    0.91
    ized
    0.91
    ０
    0.90
    )$
    0.89
    ore
    0.88
    9
    0.87
     Что
    0.86
    :
    0.86
    POSITIVE LOGITS
    é
    1.37
    p
    1.34
    ли
    1.23
    li
    1.22
    le
    1.20
    ll
    1.17
    ව
    1.16
    h
    1.16
    يد
    1.09
    m
    1.09
    Act Density 0.000%

    No Known Activations