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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to percentages and statistical measurements

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

    Numeric ranges

    np_acts-logits-general · gemini-2.0-flash

    ranges from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.62
    expandindo
    -0.61
     AssemblyCulture
    -0.58
    WebElementEntity
    -0.58
     урна
    -0.57
    Composable
    -0.56
    TagMode
    -0.55
    principalTable
    -0.54
    InjectAttribute
    -0.53
    -0.52
    POSITIVE LOGITS
     addirittura
    0.86
     unlimited
    0.85
     zelfs
    0.77
    unlimited
    0.76
     nawet
    0.75
     sogar
    0.72
     jopa
    0.71
     even
    0.70
     bahkan
    0.68
     upwards
    0.68
    Act Density 0.393%

    No Known Activations