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

    Neuronpedia

    INDEX
    Explanations

    commands and terminology related to programming and installation processes

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

    reviewed, served, installing, migration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mpä
    -0.50
    처럼
    -0.49
     שוליים
    -0.48
    Tembelea
    -0.47
     ervoor
    -0.47
     nonUne
    -0.45
     '\\;'
    -0.45
     ocze
    -0.44
    ❋
    -0.44
    预计
    -0.44
    POSITIVE LOGITS
     leaſt
    0.41
     reaſon
    0.38
     pleaſure
    0.36
     myſelf
    0.35
     itſelf
    0.35
     himſelf
    0.34
     fhew
    0.33
    SwitchCompat
    0.32
     continuity
    0.31
     Diſ
    0.30
    Act Density 0.246%

    No Known Activations