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

    Neuronpedia

    INDEX
    Explanations

    occurrences of significant numeric values or statistics

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

    Numbers followed by a unit of measure

    np_acts-logits-general · gemini-2.0-flash

    numbers and dollars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     article
    -0.97
     example
    -0.94
     array
    -0.93
     opportunity
    -0.91
     altar
    -0.90
     answer
    -0.90
     album
    -0.90
     angle
    -0.89
     error
    -0.89
     argument
    -0.88
    POSITIVE LOGITS
    humanité
    0.50
    extérieur
    0.48
    entraînement
    0.47
    égard
    0.46
    automne
    0.45
    attente
    0.45
    hébergement
    0.44
    esterno
    0.43
    assemblée
    0.42
    enfance
    0.42
    Act Density 0.077%

    No Known Activations