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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables

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

    Mathematical expressions or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas and multilingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plus
    -0.51
    BorderFactory
    -0.48
    OrderDetails
    -0.46
    ANTH
    -0.45
     estekak
    -0.44
     Fore
    -0.43
     поза
    -0.43
    ownic
    -0.42
     eye
    -0.42
     quench
    -0.41
    POSITIVE LOGITS
     HasFactory
    0.73
    xase
    0.69
     Grecs
    0.69
     privées
    0.67
     dunque
    0.67
     onCancelled
    0.66
    saraba
    0.65
     يتيمه
    0.65
     оригіналу
    0.65
     Dostupné
    0.65
    Act Density 0.565%

    No Known Activations