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

    Neuronpedia

    INDEX
    Explanations

    wake

    np_max-act · gemini-2.0-flash

    This neuron detects words referring to physiological arousal and wakefulness states (e.g., arousal, alertness, wakefulness).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alled
    -0.06
     economics
    -0.06
    _demand
    -0.06
     indebted
    -0.06
    heap
    -0.06
     back
    -0.06
     barbecue
    -0.06
    .metroLabel
    -0.06
     assassin
    -0.06
     Mills
    -0.06
    POSITIVE LOGITS
    iter
    0.07
    RetVal
    0.07
    ΑΓ
    0.06
    precation
    0.06
     Fib
    0.06
     �
    0.06
     Activ
    0.06
    維
    0.06
    預
    0.06
    ITER
    0.06
    Act Density 0.005%

    No Known Activations