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

    Neuronpedia

    INDEX
    Explanations

    react app component definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.56
    q
    1.52
    ad
    1.44
    त
    1.40
    putting
    1.19
    per
    1.18
    un
    1.17
    ang
    1.14
    ء
    1.14
    а
    1.13
    POSITIVE LOGITS
     amused
    1.55
    niers
    1.54
     Более
    1.50
     Соответ
    1.46
     Вме
    1.45
    ually
    1.43
    рованных
    1.42
     hoax
    1.42
     Deserialize
    1.42
     grateful
    1.41
    Act Density 0.006%

    No Known Activations