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

    Neuronpedia

    INDEX
    Explanations

    characteristics and elements

    np_max-act · gemini-2.0-flash

    The neuron activates on Russian plural noun endings (e.g. the “-ы” suffix).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    بر
    -0.06
    TeV
    -0.06
    .logo
    -0.06
    Direction
    -0.06
    	glog
    -0.06
     nech
    -0.06
    mav
    -0.06
    lz
    -0.06
     Stand
    -0.06
    观
    -0.06
    POSITIVE LOGITS
    aurus
    0.07
     às
    0.07
     آثار
    0.06
    KE
    0.06
    ynchronize
    0.06
     Donate
    0.06
     Graphics
    0.06
     Figures
    0.06
    igraphy
    0.06
    া
    0.06
    Act Density 0.046%

    No Known Activations