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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and their attributes

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

    "don't" or "doesn't" follows activating token

    np_acts-logits-general · gemini-2.0-flash

    negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.59
     Debe
    -0.48
    typeorm
    -0.45
    emas
    -0.45
    featureID
    -0.44
    AsUp
    -0.43
    orso
    -0.42
    illable
    -0.42
     BERNAMA
    -0.42
    toContain
    -0.42
    POSITIVE LOGITS
     don
    2.71
     doesn
    2.48
    don
    2.18
    doesn
    2.12
     didn
    2.04
    Don
    1.94
     Don
    1.90
     Doesn
    1.89
     won
    1.84
     DON
    1.82
    Act Density 0.600%

    No Known Activations