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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing colors and appearances

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

    colors like xish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.49
     purpoſe
    -0.48
     Jefus
    -0.48
    erçe
    -0.47
     Majefty
    -0.47
     houſe
    -0.47
     Komunikasi
    -0.46
     kolye
    -0.46
     kağıdı
    -0.46
     skola
    -0.45
    POSITIVE LOGITS
    neurial
    0.73
    mistic
    0.61
     bluish
    0.60
     AssemblyCulture
    0.59
    styleType
    0.59
     Californian
    0.55
    ilistic
    0.54
    omeric
    0.54
    funky
    0.54
    athery
    0.53
    Act Density 0.026%

    No Known Activations