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

    Neuronpedia

    INDEX
    Explanations

    connections between various entities or concepts

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

    Comes after a math operator or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    mathematical and logical operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     density
    -0.80
     democracy
    -0.80
     démocratique
    -0.78
     Daniel
    -0.75
     departments
    -0.74
     defense
    -0.73
     defensively
    -0.73
     Density
    -0.73
     David
    -0.73
     democratic
    -0.72
    POSITIVE LOGITS
     Monfieur
    0.58
    zegorz
    0.53
    SequentialGroup
    0.48
     iſt
    0.47
     ſmall
    0.47
     Majefty
    0.47
     (!__
    0.46
     muualla
    0.45
     auffi
    0.45
     Chwiliwch
    0.45
    Act Density 0.399%

    No Known Activations