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

    Neuronpedia

    INDEX
    Explanations

    mentions of "usage" or variations thereof in various contexts

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

    resource usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arrête
    -0.46
     coronel
    -0.42
     Relaciones
    -0.41
     namorado
    -0.40
    Égypte
    -0.39
    extrémité
    -0.38
     Krzyż
    -0.37
     cimetière
    -0.37
     /\.
    -0.36
    #
    -0.35
    POSITIVE LOGITS
    Usage
    2.84
     Usage
    2.67
    usage
    2.55
     usage
    2.38
     USAGE
    2.23
    USAGE
    2.14
     usages
    1.84
    usages
    1.68
     Uso
    1.30
    Uso
    1.29
    Act Density 0.004%

    No Known Activations