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

    Neuronpedia

    INDEX
    Explanations

    start, began, next, first, last

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ळून
    0.40
    zigen
    0.39
     ensuing
    0.37
     mendatang
    0.36
     সভায়
    0.36
     بده
    0.36
    🎍
    0.36
    bidden
    0.36
     ভুলে
    0.36
    zah
    0.36
    POSITIVE LOGITS
     began
    0.73
    开始
    0.63
     started
    0.62
    เริ่ม
    0.62
     commencé
    0.61
     começou
    0.61
     begun
    0.59
     começ
    0.58
     började
    0.58
    開始
    0.58
    Act Density 0.303%

    No Known Activations