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

    Neuronpedia

    INDEX
    Explanations

    frame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ViewModel
    -0.08
    יאות
    -0.08
     عبدال
    -0.08
    罾
    -0.07
     ResourceManager
    -0.07
    嗔
    -0.07
    魃
    -0.07
    adv
    -0.07
     Babe
    -0.07
    寺
    -0.07
    POSITIVE LOGITS
     Reception
    0.08
    แผน
    0.07
    _);↵↵
    0.07
     אתם
    0.07
    unga
    0.07
    ('//
    0.07
     safely
    0.07
     Landing
    0.06
    乱象
    0.06
    forth
    0.06
    Act Density 0.002%

    No Known Activations