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

    Neuronpedia

    INDEX
    Explanations

    Alpaca

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ornia
    0.45
    ندق
    0.41
    يار
    0.40
    ru
    0.40
    ABP
    0.39
     Pint
    0.39
    lens
    0.39
    ormal
    0.38
    ಂತೆ
    0.38
    ienta
    0.38
    POSITIVE LOGITS
     pac
    0.96
     Pac
    0.89
     PAC
    0.89
    PAC
    0.89
    Pac
    0.89
    pac
    0.88
     PACS
    0.78
    acs
    0.70
    PACS
    0.69
     BAC
    0.62
    Act Density 0.001%

    No Known Activations