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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to scientific measurements and structures

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

    counting or measuring

    np_acts-logits-general · gemini-2.0-flash

    counting discrete units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Према
    -0.75
     ujednoznacz
    -0.72
    SourceChecksum
    -0.62
    MethodManager
    -0.61
    AndEndTag
    -0.60
     propOrder
    -0.59
    duled
    -0.59
    WriteTagHelper
    -0.57
    IVED
    -0.57
     gar
    -0.56
    POSITIVE LOGITS
    count
    0.77
     count
    0.74
    zahl
    0.68
     Counts
    0.67
     counts
    0.67
    Count
    0.66
     COUNT
    0.60
    COUNT
    0.60
     Count
    0.59
     counted
    0.56
    Act Density 0.963%

    No Known Activations