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

    Neuronpedia

    INDEX
    Explanations

    instances of light and brightness, often in relation to illumination and visibility

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

    after "shed" or related to "light"

    np_acts-logits-general · gemini-2.0-flash

    shed light on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.60
    archiviato
    -0.50
    execSQL
    -0.49
    writeFieldEnd
    -0.48
    etna
    -0.46
    ollectionView
    -0.45
    Transkript
    -0.45
     getItemCount
    -0.45
    enterOuterAlt
    -0.44
     bVar
    -0.44
    POSITIVE LOGITS
     lighting
    1.88
     lights
    1.84
     illumination
    1.82
     light
    1.70
     Lighting
    1.67
    Lighting
    1.63
    lights
    1.59
     darkness
    1.59
     illuminate
    1.58
    light
    1.58
    Act Density 0.235%

    No Known Activations