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

    Neuronpedia

    INDEX
    Explanations

    Python and string processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dzie
    0.51
    0.48
    iyesi
    0.47
     with
    0.47
    인
    0.46
    ড
    0.46
    SHORT
    0.45
    ২
    0.45
    with
    0.45
    langan
    0.45
    POSITIVE LOGITS
     Braves
    0.52
    燊
    0.46
    ampunk
    0.44
     برش
    0.43
    itization
    0.43
    ppler
    0.42
     Gründen
    0.41
     Mathematical
    0.41
     approachable
    0.41
     BRCA
    0.41
    Act Density 0.000%

    No Known Activations