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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens forming the placeholder user name (patterns like “NAME_1,” “NAME_2,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ICY
    -0.07
     Moz
    -0.06
    ena
    -0.06
     detained
    -0.06
    >`;↵
    -0.06
     Hoàng
    -0.06
    ontology
    -0.06
    Pages
    -0.06
    aj
    -0.06
    ざ
    -0.06
    POSITIVE LOGITS
    (actual
    0.07
    _SEGMENT
    0.07
    POINT
    0.06
     инвести
    0.06
     wager
    0.06
    SB
    0.06
     bets
    0.06
    cleanup
    0.06
     observable
    0.06
    Additional
    0.06
    Act Density 0.020%

    No Known Activations