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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of official health authorities or agencies—especially “Ministry of Health” (and similar institutional names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    蜘蛛
    -0.06
    _hub
    -0.06
    _functions
    -0.06
     女
    -0.06
     นาง
    -0.06
     Rape
    -0.06
     sluggish
    -0.06
    败
    -0.06
    ippy
    -0.06
     Drew
    -0.06
    POSITIVE LOGITS
     Ministry
    0.09
     beside
    0.07
    IGNAL
    0.07
     Apart
    0.07
     professions
    0.07
    sembl
    0.06
    овая
    0.06
     advoc
    0.06
    @@@@
    0.06
     понад
    0.06
    Act Density 0.010%

    No Known Activations