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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oral
    -0.07
    公園
    -0.07
    pared
    -0.07
    _voice
    -0.06
    hev
    -0.06
     kullanı
    -0.06
    `);↵↵
    -0.06
     damage
    -0.06
     Bull
    -0.06
    hů
    -0.06
    POSITIVE LOGITS
    AdapterFactory
    0.06
     estaba
    0.06
    gone
    0.06
     Democracy
    0.06
    estruct
    0.06
    .AppSettings
    0.06
     Establishment
    0.06
    мами
    0.06
     geographical
    0.06
    इसक
    0.06
    Act Density 0.030%

    No Known Activations