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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Николай
    0.41
    禟
    0.40
     việc
    0.39
     dueDate
    0.39
    ходов
    0.39
     став
    0.38
     majeur
    0.38
     emozioni
    0.37
     관계로
    0.37
     emociones
    0.36
    POSITIVE LOGITS
    lowest
    0.40
    empty
    0.37
    smallest
    0.37
    running
    0.37
     lowest
    0.36
    secs
    0.35
    ■
    0.34
     smallest
    0.34
    portion
    0.33
     overlapped
    0.33
    Act Density 0.005%

    No Known Activations