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

    Neuronpedia

    INDEX
    Explanations

    Paralympic categories

    np_max-act · gemini-2.0-flash

    the neuron detects alphanumeric codes or model/class identifiers (e.g. tokens beginning with a letter followed by digits)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    им
    -0.07
     xbmc
    -0.07
    icode
    -0.07
     trx
    -0.07
     NVIDIA
    -0.07
    -ring
    -0.07
    (control
    -0.06
    creen
    -0.06
    아파트
    -0.06
     sens
    -0.06
    POSITIVE LOGITS
    .AppCompatActivity
    0.07
    (hostname
    0.07
    ('.');↵
    0.07
    _Version
    0.07
    .removeClass
    0.06
    fillable
    0.06
     Sham
    0.06
     нерв
    0.06
    .started
    0.06
    мерикан
    0.06
    Act Density 0.066%

    No Known Activations