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

    Neuronpedia

    INDEX
    Explanations

    patterns associated with mathematical or computational expressions

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

    numbers between symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.77
    tagHelperRunner
    -0.73
    TagMode
    -0.61
     Савезне
    -0.60
     zelve
    -0.55
    parsedMessage
    -0.54
    новништво
    -0.53
    цездатний
    -0.52
    adaptiveStyles
    -0.52
     Wicidata
    -0.51
    POSITIVE LOGITS
     last
    0.42
     Balance
    0.41
     corners
    0.41
     BALANCE
    0.41
    OfThe
    0.39
    intios
    0.39
     linger
    0.39
     later
    0.39
     balance
    0.38
     lord
    0.37
    Act Density 0.094%

    No Known Activations