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

    Neuronpedia

    INDEX
    Explanations

    body-parser

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    렇게
    1.20
    ü
    1.16
    로서
    1.04
    ným
    1.01
    üle
    1.00
    चा
    0.97
    การ
    0.96
     scoperto
    0.96
    सभी
    0.95
     livelli
    0.95
    POSITIVE LOGITS
    ل
    1.02
    agation
    1.02
    ன்த
    1.01
    احة
    1.00
     extensible
    1.00
    の一部
    0.99
    ью
    0.98
    ugd
    0.98
    encoded
    0.98
     modulated
    0.97
    Act Density 0.000%

    No Known Activations