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

    Neuronpedia

    INDEX
    Explanations

    important statements and recommendations

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

    after "should," "worth," or "be."

    np_acts-logits-general · gemini-2.0-flash

    phrases introducing facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.90
    tvguidetime
    -0.87
    WireFormatLite
    -0.70
    Portail
    -0.65
    出版年
    -0.62
    Биография
    -0.62
    writeFieldEnd
    -0.60
     makeStyles
    -0.60
    OGND
    -0.59
    */
    -0.59
    POSITIVE LOGITS
     note
    2.67
     Note
    2.35
    note
    2.23
    Note
    2.18
     NOTE
    1.85
     remember
    1.82
    NOTE
    1.75
     notes
    1.66
     notice
    1.61
     Remember
    1.56
    Act Density 0.658%

    No Known Activations