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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and their patterns

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

    month names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Auß
    -0.44
     prefeito
    -0.44
     Händler
    -0.44
    ontan
    -0.40
     miliardi
    -0.40
     giras
    -0.40
     zwart
    -0.40
     Duft
    -0.40
     Survivors
    -0.39
     Binnen
    -0.39
    POSITIVE LOGITS
     purpoſe
    0.65
     pleaſure
    0.60
     Reſ
    0.54
    forKey
    0.51
     ESR
    0.50
     myſelf
    0.50
     հղումներ
    0.50
    ElementException
    0.49
     fubject
    0.48
    笛
    0.47
    Act Density 0.074%

    No Known Activations