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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    注意到
    -0.07
    .INFO
    -0.07
    ouncy
    -0.07
     cornerstone
    -0.07
    阪
    -0.07
    也是一种
    -0.07
    -common
    -0.07
    anko
    -0.06
    pered
    -0.06
    动摇
    -0.06
    POSITIVE LOGITS
    sizes
    0.07
    cycles
    0.07
     Physiology
    0.07
    ♬
    0.07
    �
    0.07
    🖨
    0.07
     storia
    0.07
     abortion
    0.07
    سياسات
    0.06
    \n
    0.06
    Act Density 0.015%

    No Known Activations