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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “user” (including tokens like user, username, and the user role in headers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Zimmerman
    -0.07
     университ
    -0.07
    [code
    -0.06
    goals
    -0.06
     governments
    -0.06
     Phillip
    -0.06
    Wer
    -0.06
     fiction
    -0.06
    타이
    -0.06
    лишком
    -0.06
    POSITIVE LOGITS
    .QRect
    0.07
    	Use
    0.07
    acerb
    0.07
     bitwise
    0.06
    _decay
    0.06
    adí
    0.06
     scé
    0.06
    視
    0.06
     backdrop
    0.06
     sem
    0.06
    Act Density 0.034%

    No Known Activations