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

    Neuronpedia

    INDEX
    Explanations

    document outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawdę
    0.42
     BOARDSIZE
    0.40
     ഇക്കാര
    0.40
     ಒಳ್ಳೆಯ
    0.39
    〟
    0.39
    sadpoetry
    0.39
     なかっ
    0.39
    ያንዳ
    0.38
    ፉ
    0.38
     Fär
    0.38
    POSITIVE LOGITS
    This
    0.65
     provides
    0.57
     This
    0.55
     Project
    0.52
     Provides
    0.52
    Provides
    0.52
     Course
    0.51
    \
    0.51
    Project
    0.50
    Course
    0.49
    Act Density 0.049%

    No Known Activations