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

    Neuronpedia

    INDEX
    Explanations

    code organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lof
    0.45
    .»
    0.45
    )».
    0.43
    ’),
    0.42
    .’
    0.41
     പോലുള്ള
    0.41
    .’”
    0.41
     SLAs
    0.41
     వంటి
    0.41
    .’’
    0.41
    POSITIVE LOGITS
     itself
    0.46
     aromat
    0.41
     corret
    0.40
     tellement
    0.40
     reversed
    0.40
    이
    0.39
     자체가
    0.38
     overall
    0.38
    本身
    0.37
     intended
    0.37
    Act Density 0.162%

    No Known Activations