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

    Neuronpedia

    INDEX
    Explanations

    concepts related to light and illumination

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

    light, shine, illumination, brightness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     נוס
    -0.33
    ässig
    -0.31
     yapıl
    -0.31
     tvar
    -0.31
     variar
    -0.31
     mismatch
    -0.31
     Grunde
    -0.30
     tø
    -0.28
    size
    -0.28
     rubber
    -0.28
    POSITIVE LOGITS
     snippetHide
    0.80
     light
    0.73
     shining
    0.73
     brightness
    0.72
     shine
    0.72
     illumination
    0.70
     LIGHT
    0.70
     betweenstory
    0.69
    light
    0.68
    Shine
    0.68
    Act Density 0.038%

    No Known Activations