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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and identifiers related to programming and software development

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

    using directive or usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はじめに
    -0.42
    jenige
    -0.41
     sogenannte
    -0.40
     orice
    -0.40
     fallu
    -0.39
    rzez
    -0.37
     gezond
    -0.37
    romeo
    -0.37
    einander
    -0.36
    seamnă
    -0.35
    POSITIVE LOGITS
     Usage
    0.63
     useContext
    0.61
    IntoConstraints
    0.60
    Билгалдахарш
    0.59
    ValueStyle
    0.57
     utilize
    0.56
     Utilization
    0.55
    outSlope
    0.55
     Utilisation
    0.55
    usec
    0.55
    Act Density 0.010%

    No Known Activations