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

    Neuronpedia

    INDEX
    Explanations

    challenge

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of organized events or themed challenges and their titles (e.g. “this month’s…theme,” challenge names, contest announcements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     صف
    -0.07
     PRESS
    -0.07
     maxLength
    -0.07
     い
    -0.06
    Micro
    -0.06
    _NOTIFICATION
    -0.06
    _correction
    -0.06
     Corps
    -0.06
    。一
    -0.06
     MF
    -0.06
    POSITIVE LOGITS
     муницип
    0.07
    ainment
    0.06
    uesto
    0.06
    �
    0.06
    _wifi
    0.06
    аран
    0.06
    .Card
    0.06
    iah
    0.06
    .className
    0.05
    doors
    0.05
    Act Density 0.013%

    No Known Activations