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

    Neuronpedia

    INDEX
    Explanations

    overdoing or excess

    np_max-act · gemini-2.0-flash

    This neuron flags non-Latin (specifically Chinese) characters or words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     هفت
    -0.07
    使用
    -0.07
     opposition
    -0.07
     handful
    -0.06
     never
    -0.06
     weeks
    -0.06
     FileNotFoundException
    -0.06
     insets
    -0.06
    .zoom
    -0.06
     daughters
    -0.06
    POSITIVE LOGITS
     엔
    0.07
     aşırı
    0.07
    expanded
    0.06
    cessive
    0.06
     İt
    0.06
     ain
    0.06
     Rin
    0.06
     cate
    0.06
     bm
    0.06
     yaw
    0.06
    Act Density 0.028%

    No Known Activations