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

    Neuronpedia

    INDEX
    Explanations

    of using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一つの
    0.52
    some
    0.50
     definitive
    0.49
    一款
    0.49
     sebuah
    0.48
     Some
    0.48
    단계
    0.47
    একটি
    0.47
    一些
    0.46
    en
    0.46
    POSITIVE LOGITS
     having
    0.60
     evaluating
    0.53
     assessing
    0.52
     being
    0.52
     waging
    0.52
     doing
    0.51
    being
    0.49
     selecting
    0.49
     upholding
    0.49
     inhabiting
    0.49
    Act Density 0.257%

    No Known Activations