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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _response
    -0.09
    Response
    -0.09
     নির্ব
    -0.09
     response
    -0.08
    response
    -0.07
     imminent
    -0.07
     issuing
    -0.07
     المناسب
    -0.07
     అంట
    -0.07
     rhy
    -0.07
    POSITIVE LOGITS
    字段
    0.14
     fields
    0.12
     Fields
    0.12
     declared
    0.11
    (fields
    0.10
     campos
    0.10
     declarations
    0.10
     поля
    0.10
    Fields
    0.10
     lateinit
    0.10
    Act Density 0.015%

    No Known Activations