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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash

    This neuron predominantly activates on occurrences of the filler/softening adverb “just.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    interpret
    -0.06
    Fi
    -0.06
    .AI
    -0.06
    **
    -0.06
    asty
    -0.06
     nếu
    -0.06
    missive
    -0.06
    ků
    -0.06
     să
    -0.06
     Pins
    -0.06
    POSITIVE LOGITS
     وش
    0.07
    subtitle
    0.06
     gadget
    0.06
    groupon
    0.06
    .GetById
    0.06
     balances
    0.06
    _cart
    0.06
    juries
    0.06
    /*
↵
    0.06
    荣
    0.06
    Act Density 0.017%

    No Known Activations