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

    Neuronpedia

    INDEX
    Explanations

    description of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    říklad
    1.25
    дак
    1.20
    gia
    1.17
    ონის
    1.17
    至于
    1.15
    ਤ
    1.14
     exem
    1.09
     urgent
    1.09
     unmistakable
    1.06
    pertensive
    1.05
    POSITIVE LOGITS
     spate
    1.23
    에
    1.08
     কপি
    1.03
    en
    1.03
    stops
    1.02
     二
    1.01
     имел
    1.01
     當
    1.01
    まぁ
    1.00
    chtigt
    0.99
    Act Density 0.000%

    No Known Activations