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

    Neuronpedia

    INDEX
    Explanations

    references to academic or scholarly resources

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

    scholarly references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WindowConstants
    -0.62
    Referencie
    -0.56
    MLLoader
    -0.50
     fat
    -0.46
     PopupWindow
    -0.45
     Env
    -0.45
     Mummy
    -0.45
     divorced
    -0.45
    prefixer
    -0.45
     Situations
    -0.44
    POSITIVE LOGITS
     Scholar
    1.67
    scholar
    1.62
    Scholar
    1.59
     scholar
    1.34
     SCHOLAR
    1.34
     scholarly
    1.23
     Scholars
    1.14
    scholars
    1.03
     SCHOL
    1.02
    Scholars
    1.01
    Act Density 0.004%

    No Known Activations