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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are parts of personal names (i.e. proper‐noun name components) in email header lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Dog
    -0.06
    ariant
    -0.06
     domains
    -0.06
    	Data
    -0.06
    MENU
    -0.06
    PropTypes
    -0.06
    irty
    -0.06
    Unc
    -0.06
    ²
    -0.06
     Names
    -0.06
    POSITIVE LOGITS
     inspector
    0.08
     capable
    0.07
     �
    0.06
    ιλ
    0.06
     �
    0.06
    _clients
    0.06
    .resolution
    0.06
     Lastly
    0.06
    .ReadAll
    0.06
    ená
    0.06
    Act Density 0.011%

    No Known Activations