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

    Neuronpedia

    INDEX
    Explanations

    references to personal or societal interests

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

    competing interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parachute
    -0.56
     diagon
    -0.56
    ünst
    -0.55
     autopsy
    -0.52
    dynam
    -0.51
    Seconds
    -0.50
    Surgical
    -0.50
    NextPage
    -0.50
     dynamite
    -0.50
     postcards
    -0.50
    POSITIVE LOGITS
     interests
    1.70
    interests
    1.43
     Interests
    1.41
    Interests
    1.24
     Interessen
    0.95
     interesses
    0.87
     intereses
    0.85
     intérêts
    0.77
     érde
    0.60
     интере
    0.59
    Act Density 0.010%

    No Known Activations