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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thứ
    -0.08
     didReceiveMemoryWarning
    -0.06
    新华网
    -0.06
    חיבור
    -0.06
    个多小时
    -0.06
    瘕
    -0.06
    陲
    -0.06
    辑
    -0.06
    𬭸
    -0.06
    espère
    -0.06
    POSITIVE LOGITS
     Egypt
    0.08
     NCAA
    0.08
    قار
    0.07
     archae
    0.07
    oste
    0.07
    _esc
    0.07
    ref
    0.07
    Scalar
    0.07
    滑
    0.07
     Ple
    0.06
    Act Density 0.115%

    No Known Activations