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

    Neuronpedia

    INDEX
    Explanations

    Okay, chatbot response starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ىم
    0.45
     ట
    0.43
    ግዳ
    0.42
    高志森
    0.41
    ോക
    0.40
    ęk
    0.40
    ሆነ
    0.39
     produkty
    0.38
    ók
    0.38
     ভর
    0.38
    POSITIVE LOGITS
     આપવામાં
    0.47
    )(
    0.42
     (
    0.41
    adians
    0.41
    ادث
    0.40
    ※
    0.40
     Facial
    0.40
     Susan
    0.39
     ADN
    0.39
    আলো
    0.39
    Act Density 0.008%

    No Known Activations