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

    Neuronpedia

    INDEX
    Explanations

    programming imports and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PhCH
    0.92
    la
    0.89
    OLYBDENUM
    0.89
     particulières
    0.88
    EVEN
    0.87
     परिणामस्वरूप
    0.86
    rically
    0.86
    setzungen
    0.84
    licher
    0.84
     ocorrer
    0.84
    POSITIVE LOGITS
     as
    1.03
    و
    1.03
    ਰ
    1.02
     and
    0.96
    ing
    0.94
    in
    0.93
     can
    0.93
     in
    0.91
    og
    0.91
     তথ্য
    0.91
    Act Density 0.046%

    No Known Activations