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

    Neuronpedia

    INDEX
    Explanations

    nearby

    np_max-act · gemini-2.0-flash

    The neuron responds when the text is describing how things are arranged or positioned (e.g. “arrangement,” “order,” “neighboring,” “placement,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sah
    -0.07
    .dim
    -0.07
     ne
    -0.07
    พน
    -0.06
    _when
    -0.06
     Nick
    -0.06
    pod
    -0.06
    plug
    -0.06
    rom
    -0.06
    ิธ
    -0.06
    POSITIVE LOGITS
    >Contact
    0.07
    یدا
    0.06
     새로운
    0.06
     대상
    0.06
    ителем
    0.06
     showToast
    0.06
    пня
    0.06
    一个人
    0.06
     içindeki
    0.06
     شرقی
    0.06
    Act Density 0.141%

    No Known Activations