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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or variability in outcomes

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

    quantities or portions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centralwidget
    -0.39
     generally
    -0.37
     usually
    -0.36
     usual
    -0.36
    otene
    -0.35
     Les
    -0.34
    proken
    -0.34
     serv
    -0.33
    wo
    -0.33
    OutOfRange
    -0.33
    POSITIVE LOGITS
    OGND
    0.65
     fometimes
    0.59
    __":
    0.58
     camiset
    0.57
    Autoritní
    0.56
    onOptions
    0.56
    บ้าง
    0.54
    GEBURTSDATUM
    0.52
     část
    0.51
     część
    0.50
    Act Density 0.482%

    No Known Activations