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

    Neuronpedia

    INDEX
    Explanations

    Qt alignment flags and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஆனால்
    0.47
     ujung
    0.46
     operasi
    0.44
    向き
    0.43
     Nhưng
    0.43
    siniz
    0.42
    陽
    0.42
     रोपवे
    0.42
     terapia
    0.42
    hi
    0.41
    POSITIVE LOGITS
    ed
    0.54
    eacute
    0.53
    𝖊
    0.51
    er
    0.48
    頖
    0.46
    cę
    0.45
    га
    0.45
     Lessons
    0.44
     praises
    0.43
    e
    0.43
    Act Density 0.000%

    No Known Activations