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

    Neuronpedia

    INDEX
    Explanations

    words associated with brightness and light

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

    shine, sparkle, shimmer, glisten

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.51
    richTextPanel
    -0.49
    IntoConstraints
    -0.49
    ConstraintMaker
    -0.49
    DockStyle
    -0.41
    FormTagHelper
    -0.41
    exitRule
    -0.40
     argparse
    -0.40
     depri
    -0.39
    anlage
    -0.39
    POSITIVE LOGITS
     shining
    1.08
     shine
    1.05
     shines
    0.98
     shone
    0.97
     Shine
    0.96
     Shining
    0.95
    Shine
    0.93
    Shining
    0.93
    shining
    0.89
     brilliance
    0.89
    Act Density 0.029%

    No Known Activations