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

    Neuronpedia

    INDEX
    Explanations

    `align` environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ona
    0.37
     कोहली
    0.33
    coli
    0.31
     Gaines
    0.31
     efektif
    0.31
     पिंडदान
    0.30
    ara
    0.30
    ció
    0.30
    Clarke
    0.30
     Chauhan
    0.30
    POSITIVE LOGITS
     fonctionnent
    0.25
    جھ
    0.24
    WE
    0.24
    적이
    0.23
     উদ
    0.23
    ᄌ
    0.23
    <0xE1>
    0.23
    BOOT
    0.23
     آس
    0.23
    程序
    0.23
    Act Density 0.000%

    No Known Activations