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

    Neuronpedia

    INDEX
    Explanations

    punctuations and other non-alphanumeric characters

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

    numbers and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.66
    GenerationType
    -0.55
     propOrder
    -0.55
    WithIOException
    -0.53
    transQ
    -0.53
     kasarigan
    -0.53
    SharedCtor
    -0.53
     wireType
    -0.51
     resourceCulture
    -0.50
    __(/*!
    -0.47
    POSITIVE LOGITS
    McDonald
    0.35
     asti
    0.35
    ccccccc
    0.34
     pizz
    0.34
    uesas
    0.34
    Secret
    0.34
    Vader
    0.34
    strophy
    0.34
    mobileqq
    0.34
     rollers
    0.33
    Act Density 0.228%

    No Known Activations