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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals with a decimal point (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     люди
    -0.06
     AssemblyCompany
    -0.06
    _pred
    -0.06
    ::::::::::::::::::::::::::::::::
    -0.06
    getDescription
    -0.06
    /security
    -0.06
     inflicted
    -0.06
    ۷
    -0.06
    PROTO
    -0.06
    щина
    -0.06
    POSITIVE LOGITS
    Nam
    0.07
    serialized
    0.07
     mph
    0.07
     бар
    0.06
     nh
    0.06
     �
    0.06
     stif
    0.06
    MW
    0.06
    rane
    0.06
     برابر
    0.06
    Act Density 0.018%

    No Known Activations