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

    Neuronpedia

    INDEX
    Explanations

    color codes and descriptions of colors

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

    "white" or its hexadecimal color code

    np_acts-logits-general · gemini-2.0-flash

    color white

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientôt
    -0.36
    sonian
    -0.36
    Xna
    -0.35
    ſchen
    -0.35
    Paran
    -0.35
     Synt
    -0.35
    licite
    -0.35
    nameof
    -0.34
    dende
    -0.34
    深度
    -0.33
    POSITIVE LOGITS
     white
    1.38
    white
    1.25
     White
    1.18
    White
    1.13
     WHITE
    1.12
    WHITE
    1.09
     whites
    1.05
     beyaz
    1.05
     whiteness
    1.02
     putih
    0.98
    Act Density 0.398%

    No Known Activations