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

    Neuronpedia

    INDEX
    Explanations

    Asking questions/help

    np_max-act · gemini-2.0-flash

    This neuron detects polite follow-up invitations offering further help (e.g. “If you have any other questions, feel free to ask!”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    控制
    -0.06
     Colleges
    -0.06
    工業
    -0.06
    ‐'
    -0.06
    かった
    -0.06
    尼亚
    -0.05
     shutdown
    -0.05
    ศาสตร
    -0.05
    成
    -0.05
    ,､
    -0.05
    POSITIVE LOGITS
     cam
    0.07
    änder
    0.07
     ตำ
    0.07
     накоп
    0.06
    .READ
    0.06
     Yeni
    0.06
     obesity
    0.06
     pomoci
    0.06
    羊
    0.06
    onald
    0.06
    Act Density 0.030%

    No Known Activations