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

    Neuronpedia

    INDEX
    Explanations

    GT and GD (abbreviations)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .segments
    -0.07
    ğitim
    -0.06
    (pkg
    -0.06
     аналог
    -0.06
    (ray
    -0.06
    LayoutParams
    -0.06
    ITU
    -0.06
    (section
    -0.06
    üny
    -0.06
    hoc
    -0.06
    POSITIVE LOGITS
     ST
    0.06
    造
    0.06
     nộp
    0.06
     SUPER
    0.06
    openid
    0.06
    //↵↵↵
    0.06
     grop
    0.06
     Global
    0.06
    QE
    0.06
     Chili
    0.06
    Act Density 0.015%

    No Known Activations