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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron detects numbered list markers (the numerals labeling ordered list items, e.g. “1.”, “2.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ly
    -0.08
    Đ
    -0.07
     onclick
    -0.07
    إن
    -0.06
     �
    -0.06
    -tools
    -0.06
     sieht
    -0.06
     retros
    -0.06
     dhcp
    -0.06
     صرف
    -0.06
    POSITIVE LOGITS
     pada
    0.07
     Palestinians
    0.07
    _TBL
    0.07
    _PICTURE
    0.06
     leash
    0.06
     کیل
    0.06
     الرسمي
    0.06
     weapons
    0.06
    饰
    0.06
    schema
    0.06
    Act Density 0.042%

    No Known Activations