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

    Neuronpedia

    INDEX
    Explanations

    quantities and numbers associated with large groups of people or things

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

    Orders of magnitude

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.72
    ArgsConstructor
    -0.60
    qrstuvwxyz
    -0.60
    complexContent
    -0.55
    UIControlState
    -0.55
    IActionResult
    -0.54
    kloped
    -0.51
    webElementGuid
    -0.51
    bootstrapcdn
    -0.51
    oxane
    -0.51
    POSITIVE LOGITS
    thousands
    1.08
     Hundreds
    1.07
     Thousands
    1.06
    millions
    1.05
     dozens
    1.05
    Hundreds
    1.05
    hundreds
    1.04
    Thousands
    1.03
     milliers
    1.02
     dizaines
    1.01
    Act Density 0.104%

    No Known Activations