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

    Neuronpedia

    INDEX
    Explanations

    one-to-one relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मान
    1.30
    تين
    1.28
    lop
    1.22
     zda
    1.21
    ت
    1.12
    tart
    1.11
    Além
    1.11
    midt
    1.09
    tod
    1.08
     Aik
    1.08
    POSITIVE LOGITS
     foram
    1.27
     mieli
    1.25
    ಿಸಲ
    1.22
    ధీ
    1.22
     kiş
    1.20
    hours
    1.19
    ১
    1.19
     bulunan
    1.18
    បាន
    1.17
    𝐎
    1.17
    Act Density 0.000%

    No Known Activations