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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and numerical expressions

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

    Numbers, possibly in arithmetic expressions

    np_acts-logits-general · gemini-2.0-flash

    algebraic expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.60
     lenker
    -0.49
     taget
    -0.45
     Bühne
    -0.44
    taget
    -0.44
    ise
    -0.44
    ation
    -0.43
     通販
    -0.43
    atimes
    -0.43
    WAH
    -0.42
    POSITIVE LOGITS
    findpost
    0.73
    UserScript
    0.61
     imageNamed
    0.61
    })->
    0.59
    \{\\
    0.58
    DrawerToggle
    0.57
     AIAA
    0.57
    InputBorder
    0.57
     oaths
    0.56
     bezeichneter
    0.55
    Act Density 0.362%

    No Known Activations