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

    Neuronpedia

    INDEX
    Explanations

    the beginning of document sections or topics

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

    Tokens after "Q" or "In"

    np_acts-logits-general · gemini-2.0-flash

    admin and administrator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulipas
    -0.51
     muualla
    -0.50
     ($(
    -0.47
    Dry
    -0.46
    Pranala
    -0.46
    yours
    -0.45
    بوابة
    -0.45
    dry
    -0.45
    DRY
    -0.44
    ="{{$
    -0.43
    POSITIVE LOGITS
     Admin
    0.89
     admin
    0.87
    admin
    0.86
    Admin
    0.85
     Administrator
    0.81
     ADMIN
    0.81
     administrator
    0.79
     Administration
    0.79
     administration
    0.77
    LookAnd
    0.73
    Act Density 0.076%

    No Known Activations