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

    Neuronpedia

    INDEX
    Explanations

    references to the term "black" and its variations in various contexts

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

    "black" followed by certain nouns

    np_acts-logits-general · gemini-2.0-flash

    black followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BibitemShut
    -1.21
     myſelf
    -1.16
    Personensuche
    -1.10
     }}"></
    -1.08
     themſelves
    -1.04
     propOrder
    -1.03
    MessageTagHelper
    -1.03
     itſelf
    -1.03
     الحره
    -1.02
    )':
    -1.02
    POSITIVE LOGITS
     Black
    1.22
    Black
    1.17
     BLACK
    1.13
    black
    1.07
    BLACK
    1.04
     black
    1.02
     Blackwell
    0.88
    a
    0.80
     Schwar
    0.76
    K
    0.73
    Act Density 0.070%

    No Known Activations