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

    Neuronpedia

    INDEX
    Explanations

    instructions and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    班
    0.50
     giết
    0.48
     sigmoid
    0.47
     名前
    0.47
     slalom
    0.47
     h
    0.46
    reactivex
    0.46
     scissor
    0.46
     trộn
    0.45
    済み
    0.45
    POSITIVE LOGITS
    ני
    0.56
    Су
    0.53
    Э
    0.53
    ا
    0.52
    এ
    0.50
    к
    0.50
    ک
    0.47
    सी
    0.46
     divergences
    0.45
    Innen
    0.45
    Act Density 0.000%

    No Known Activations