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

    Neuronpedia

    INDEX
    Explanations

    beard

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on mentions of “beard,” i.e. it detects the word “beard” (and its variants) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (sf
    -0.07
    _sms
    -0.06
    Türk
    -0.06
    Moon
    -0.06
     Gone
    -0.06
    .paginator
    -0.06
     htt
    -0.06
     Trafford
    -0.06
     Facility
    -0.06
    (mapping
    -0.06
    POSITIVE LOGITS
     beard
    0.10
     Beard
    0.09
     мав
    0.08
    \:
    0.07
     presenting
    0.07
     умов
    0.06
    adder
    0.06
     Brill
    0.06
     فعالیت
    0.06
    -save
    0.06
    Act Density 0.005%

    No Known Activations