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

    Neuronpedia

    INDEX
    Explanations

    text formatting or document references

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

    "Return to text"

    np_acts-logits-general · gemini-2.0-flash

    return to text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.96
    bootstrapcdn
    -0.93
    featureID
    -0.93
     invokingState
    -0.85
     kasarigan
    -0.83
     ویکی‌پدی
    -0.82
    transQ
    -0.81
     autorytatywna
    -0.80
    脚注の使い方
    -0.80
    contentLoaded
    -0.79
    POSITIVE LOGITS
    1
    0.32
     again
    0.30
    又
    0.29
     //$
    0.28
    ');
    0.28
    Ex
    0.28
    No
    0.28
    2
    0.28
    ()];
    0.28
    блон
    0.28
    Act Density 0.793%

    No Known Activations