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

    Neuronpedia

    INDEX
    Explanations

    engineering components or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱓
    0.57
    lockSeconds
    0.55
     polypes
    0.55
    有名
    0.53
    ற்று
    0.52
    स्‍या
    0.52
     сегодня
    0.52
     noirâtre
    0.51
    扱う
    0.49
    𒌆
    0.49
    POSITIVE LOGITS
    re
    0.64
    c
    0.58
    ↵
    0.53
     Components
    0.51
    s
    0.50
    ’
    0.49
     f
    0.49
     a
    0.48
     Component
    0.48
    per
    0.47
    Act Density 0.001%

    No Known Activations