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

    Neuronpedia

    INDEX
    Explanations

    names and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awiają
    1.07
    újo
    1.05
    štu
    1.05
    ésil
    1.04
    geoType
    1.04
    ancı
    1.03
    áře
    1.03
    ೇಶ್
    1.02
    ánica
    1.02
    െല്ലാം
    1.02
    POSITIVE LOGITS
    ?
    1.39
     The
    1.30
    The
    1.28
    !
    1.16
    .?
    1.00
    is
    0.91
     THE
    0.89
    ↵↵
    0.88
    '
    0.84
    in
    0.82
    Act Density 0.000%

    No Known Activations