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

    Neuronpedia

    INDEX
    Explanations

    terms related to modeling and mathematical models

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

    modeling and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haup
    -0.43
    oplayer
    -0.42
    뀔
    -0.39
     препратки
    -0.39
     optionally
    -0.38
    TableBody
    -0.37
     bâton
    -0.36
     Maj
    -0.36
    quias
    -0.36
    <bos>
    -0.35
    POSITIVE LOGITS
     Model
    0.62
     model
    0.59
    Modeling
    0.56
     modeling
    0.56
     Modeling
    0.54
     modelling
    0.54
     Modelling
    0.53
     ExecuteAsync
    0.52
    TagMode
    0.52
    UnusedPrivate
    0.52
    Act Density 0.065%

    No Known Activations