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

    Neuronpedia

    INDEX
    Explanations

    key phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    惑星
    0.46
     rispond
    0.46
    වත
    0.46
     cadeira
    0.45
    лкой
    0.45
     blanchâtre
    0.44
    方面
    0.43
    ví
    0.43
    ､
    0.43
     れる
    0.43
    POSITIVE LOGITS
    s
    0.51
     Wrest
    0.47
     book
    0.46
    த்
    0.45
     Libro
    0.44
     Summary
    0.44
     Aank
    0.44
     Book
    0.43
     همچنین
    0.43
    shit
    0.42
    Act Density 0.000%

    No Known Activations