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

    Neuronpedia

    INDEX
    Explanations

    database query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.05
    elt
    1.05
    är
    0.98
    res
    0.97
    oir
    0.95
    ш
    0.92
    riy
    0.89
    <0xAB>
    0.89
    لي
    0.83
    urring
    0.83
    POSITIVE LOGITS
    ות
    1.53
    ים
    1.36
     query
    1.31
    Query
    1.15
    is
    1.12
     queries
    1.09
    A
    1.05
    కు
    1.03
     arquivos
    1.03
    H
    1.02
    Act Density 0.027%

    No Known Activations