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

    Neuronpedia

    INDEX
    Explanations

    references or citations within scientific documents

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

    figure panel references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insuffisamment
    -0.45
    ToEnd
    -0.41
    archiviato
    -0.41
     Stein
    -0.40
    °.
    -0.39
     BorderSide
    -0.38
    EndContext
    -0.37
    исленность
    -0.36
    .”
    -0.36
     River
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.56
    ValueStyle
    0.52
    expandindo
    0.50
     Roskov
    0.50
    Aiheesta
    0.49
     HttpNotFound
    0.48
     autorytatywna
    0.47
     Italijani
    0.46
    LabelTagHelper
    0.45
    🔕
    0.45
    Act Density 0.043%

    No Known Activations