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

    Neuronpedia

    INDEX
    Explanations

    colorful and glowing attributes in descriptions

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

    Colors

    np_acts-logits-general · gemini-2.0-flash

    colors and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.59
    verifyException
    -0.46
     NKC
    -0.46
     direta
    -0.46
     RemoteException
    -0.42
     createSlice
    -0.42
    lankton
    -0.42
    ↴
    -0.42
    hability
    -0.41
    ➟
    -0.41
    POSITIVE LOGITS
     yellow
    0.57
     white
    0.53
    yellow
    0.51
     pinulongan
    0.51
     brown
    0.50
     pink
    0.48
     weiße
    0.48
     Yellow
    0.46
     purple
    0.45
    white
    0.45
    Act Density 0.188%

    No Known Activations