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

    Neuronpedia

    INDEX
    Explanations

    regional or degree modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    చన
    0.49
    ಉ
    0.45
    anye
    0.44
     coincides
    0.42
    ትር
    0.42
    𒀊
    0.41
    Escape
    0.41
    트는
    0.41
    潺
    0.41
     لوبې
    0.41
    POSITIVE LOGITS
     Butter
    0.43
     Done
    0.42
     Pokémon
    0.41
     minder
    0.41
     ana
    0.41
     wafer
    0.41
     Raya
    0.41
     Twe
    0.40
    ordre
    0.40
     seu
    0.40
    Act Density 0.001%

    No Known Activations