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

    Neuronpedia

    INDEX
    Explanations

    Another

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    惭
    -0.08
     행복
    -0.07
     spring
    -0.07
     visible
    -0.07
     illusion
    -0.07
    公里
    -0.07
    相对
    -0.07
     seedu
    -0.06
    昃
    -0.06
    emplate
    -0.06
    POSITIVE LOGITS
     another
    0.09
     Another
    0.07
    Another
    0.07
     aby
    0.07
    another
    0.07
    mys
    0.07
    🗽
    0.06
    0.06
    谈论
    0.06
    ={"
    0.06
    Act Density 0.034%

    No Known Activations