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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects sentences stating the study’s purpose or objectives (i.e. goal/aim statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     site
    -0.07
     expanded
    -0.07
     expire
    -0.07
    SSERT
    -0.06
    ۵
    -0.06
     spring
    -0.06
    .active
    -0.06
    elivery
    -0.06
    \db
    -0.06
    deployment
    -0.06
    POSITIVE LOGITS
    (balance
    0.07
     Alic
    0.06
     견
    0.06
     Derek
    0.06
    ;;↵↵
    0.06
     Swap
    0.06
     وقد
    0.06
    Apart
    0.06
     Peygamber
    0.06
     bardzo
    0.06
    Act Density 0.120%

    No Known Activations