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

    Neuronpedia

    INDEX
    Explanations

    appropriateness

    np_max-act · gemini-2.0-flash

    This neuron remains inactive on all input tokens and does not respond to any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Simple
    -0.07
     Sheep
    -0.07
     CELL
    -0.07
    球
    -0.06
     particle
    -0.06
     Rotate
    -0.06
    Hard
    -0.06
     rebels
    -0.06
     maintenance
    -0.06
     presentation
    -0.06
    POSITIVE LOGITS
    λεκ
    0.06
    ा.↵
    0.06
     наш
    0.06
     จะ
    0.06
    Xã
    0.06
     тран
    0.06
     :)↵
    0.06
     แก
    0.06
     순간
    0.06
     ож
    0.06
    Act Density 0.027%

    No Known Activations