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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantitative data and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding specific units of measurement

    np_acts-logits-general · gemini-2.0-flash

    outcomes and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.40
     innere
    -0.40
     Вікіпе
    -0.39
    énario
    -0.37
     esterna
    -0.37
     galinha
    -0.36
    เดิม
    -0.35
     místa
    -0.35
     terminal
    -0.34
     poly
    -0.34
    POSITIVE LOGITS
    windowFixed
    0.53
    󠁣
    0.51
     faſt
    0.49
    RTLU
    0.48
     purpoſe
    0.48
    ViewFeatures
    0.48
    ValueStyle
    0.48
     ✭✭
    0.47
     arşivlendi
    0.47
    WithIOException
    0.45
    Act Density 0.917%

    No Known Activations