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

    Neuronpedia

    INDEX
    Explanations

    references to eclipses and associated phenomena

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

    eclipse and overshadow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นด์
    -0.38
     للمعارف
    -0.36
     jongen
    -0.36
    yorsunuz
    -0.35
     FetchType
    -0.34
    umented
    -0.33
    romyalgia
    -0.31
    LabelTagHelper
    -0.31
    mtable
    -0.31
    vignon
    -0.31
    POSITIVE LOGITS
     eclipse
    1.80
     eclips
    1.60
     eclip
    1.51
     Eclipse
    1.45
    Eclipse
    1.26
    eclipse
    1.09
     overshadow
    0.94
    clips
    0.89
    lipse
    0.84
     overshadowed
    0.84
    Act Density 0.015%

    No Known Activations