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

    Neuronpedia

    INDEX
    Explanations

    judicious understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whilst
    0.40
     جدید
    0.39
    欸
    0.39
     została
    0.38
     Whilst
    0.38
    adult
    0.37
    towards
    0.37
     wê
    0.37
     whilst
    0.37
    ulfill
    0.36
    POSITIVE LOGITS
     intuit
    0.57
     intu
    0.54
     astute
    0.54
     judicious
    0.52
     intuitive
    0.52
     ingenious
    0.52
    intuitive
    0.52
     shrewd
    0.52
     leaping
    0.51
     guessing
    0.50
    Act Density 0.001%

    No Known Activations