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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements and statistics related to health outcomes

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

    a contrast or exception

    np_acts-logits-general · gemini-2.0-flash

    contrast or opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saus
    -0.43
    الحياه
    -0.41
     ErrIntOverflow
    -0.39
    olph
    -0.38
    zis
    -0.37
     Erm
    -0.36
     Tapa
    -0.36
    omitempty
    -0.36
    اخت
    -0.36
    getattr
    -0.36
    POSITIVE LOGITS
     instead
    0.57
    GOTREF
    0.56
     nevertheless
    0.54
    instead
    0.52
     зато
    0.52
    WebVitals
    0.49
     revanche
    0.48
    却是
    0.47
    倒是
    0.46
    卻
    0.45
    Act Density 1.283%

    No Known Activations