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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of lightness or light-related qualities

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

    light followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     companyId
    -0.62
     betweenstory
    -0.59
    retudo
    -0.56
     endwhile
    -0.54
    evos
    -0.54
    たった
    -0.51
     endfor
    -0.51
    geddon
    -0.51
     GenerationType
    -0.50
     endforeach
    -0.50
    POSITIVE LOGITS
    Light
    1.66
     light
    1.63
    light
    1.59
     Light
    1.55
     LIGHT
    1.43
    LIGHT
    1.39
     licht
    1.01
    lighter
    0.96
    Licht
    0.94
    ligh
    0.89
    Act Density 0.020%

    No Known Activations