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

    Neuronpedia

    INDEX
    Explanations

    media descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    掌柜
    -0.07
    对人体
    -0.07
    팃
    -0.07
    卫健
    -0.07
    핵
    -0.07
    口中
    -0.07
     этом
    -0.06
    泡泡
    -0.06
    切换
    -0.06
    Blockly
    -0.06
    POSITIVE LOGITS
     سنوات
    0.07
     Pradesh
    0.07
     FB
    0.07
     Articles
    0.07
    positions
    0.07
     BCE
    0.07
     TRANS
    0.07
     compassion
    0.07
     Jenn
    0.06
    AH
    0.06
    Act Density 0.007%

    No Known Activations