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

    Neuronpedia

    INDEX
    Explanations

    mongodb database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PPh
    0.93
    IN
    0.93
    pand
    0.88
     llegado
    0.88
    它
    0.86
    0.86
    Halloween
    0.86
     Tetapi
    0.83
     vei
    0.81
    THING
    0.80
    POSITIVE LOGITS
    ে
    1.20
    و
    1.06
    м
    1.00
    ен
    0.95
    на
    0.95
    ра
    0.95
    ان
    0.93
    ರ
    0.90
    ล
    0.90
     handout
    0.89
    Act Density 0.002%

    No Known Activations