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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens relating to marriage and offspring sections in biographical entries (e.g. “married,” “firstly,” “secondly,” “marriages,” “issue”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     至
    -0.07
     profitability
    -0.06
    .called
    -0.06
    Anything
    -0.06
     ASC
    -0.06
     ponds
    -0.06
    <Address
    -0.06
    ває
    -0.06
     Fac
    -0.06
    */,↵
    -0.06
    POSITIVE LOGITS
    _checker
    0.07
    quoted
    0.06
    Clr
    0.06
     Barbar
    0.06
    λογή
    0.06
    .notifications
    0.06
    -check
    0.06
    gmt
    0.06
    -null
    0.06
    _tunnel
    0.06
    Act Density 0.008%

    No Known Activations