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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getline
    -0.07
    addle
    -0.07
    Receipt
    -0.07
    .students
    -0.07
    _Style
    -0.07
    Grad
    -0.06
     Grad
    -0.06
    height
    -0.06
     Nielsen
    -0.06
     Phantom
    -0.06
    POSITIVE LOGITS
     h�
    0.07
     леж
    0.07
     göz
    0.06
     땅
    0.06
    онах
    0.06
     gek
    0.06
     Kıs
    0.06
     왔
    0.06
     เพราะ
    0.06
     잘
    0.06
    Act Density 0.014%

    No Known Activations