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

    Neuronpedia

    INDEX
    Explanations

    -Encoding

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “Content-Transfer-Encoding:” header label.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ッツ
    -0.07
    ेन
    -0.07
    tournament
    -0.07
    الأ
    -0.06
    	nodes
    -0.06
    ulsive
    -0.06
     Möglichkeit
    -0.06
     veřej
    -0.06
    "])↵↵
    -0.06
    NES
    -0.06
    POSITIVE LOGITS
     Episode
    0.07
    orry
    0.07
    寄
    0.07
     Tobacco
    0.07
     triệu
    0.07
     Owner
    0.07
    =tf
    0.06
     choking
    0.06
     Khoa
    0.06
     kanal
    0.06
    Act Density 0.000%

    No Known Activations