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

    Neuronpedia

    INDEX
    Explanations

    course of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最も
    0.49
    あなたは
    0.46
     encountered
    0.46
     Begriff
    0.46
    typically
    0.44
     stets
    0.43
     apparaissent
    0.43
     denotes
    0.43
    the
    0.41
     aristocratic
    0.41
    POSITIVE LOGITS
     نحاول
    0.61
     kiddos
    0.57
     хочу
    0.54
     কিছুটা
    0.53
    的一些
    0.52
     немного
    0.52
     तैयारी
    0.52
    我们需要
    0.52
     আগামী
    0.52
     ఎలా
    0.52
    Act Density 0.062%

    No Known Activations