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

    Neuronpedia

    INDEX
    Explanations

    description of entities and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    லிய
    0.43
     ايه
    0.40
    Под
    0.40
    utzt
    0.40
    Информация
    0.40
    Під
    0.40
    INFORMATION
    0.39
    দম
    0.39
     thePack
    0.39
    ುದು
    0.39
    POSITIVE LOGITS
     nor
    0.40
    çada
    0.38
     Edwards
    0.38
     smer
    0.38
     Ceiling
    0.38
     si
    0.38
     மறு
    0.37
     Lately
    0.37
    hind
    0.37
     sublime
    0.36
    Act Density 0.002%

    No Known Activations