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

    Neuronpedia

    INDEX
    Explanations

    instances of the symbol "+" in mathematical expressions

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

    mathematical indices and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.89
    الحياه
    -0.88
     незавершена
    -0.86
     PeEnEo
    -0.84
     الحره
    -0.83
     للاسماء
    -0.82
    Personensuche
    -0.77
    Autoritní
    -0.75
     Италијани
    -0.74
     ✭✭
    -0.70
    POSITIVE LOGITS
     gezet
    0.30
     gekomen
    0.29
     step
    0.29
     sola
    0.28
    step
    0.28
    之
    0.27
    alegal
    0.27
     zetten
    0.27
    suggestion
    0.27
    Stepper
    0.26
    Act Density 0.014%

    No Known Activations