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

    Neuronpedia

    INDEX
    Explanations

    SQL code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🔺
    -0.08
     sweat
    -0.07
     brainstorm
    -0.07
     buf
    -0.07
    "k
    -0.07
    Classic
    -0.07
    伪
    -0.07
    意见反馈
    -0.07
    帅哥
    -0.06
    mlx
    -0.06
    POSITIVE LOGITS
    就能够
    0.07
     currentNode
    0.07
    ἣ
    0.06
    蚄
    0.06
     egy
    0.06
     обраща
    0.06
    /Header
    0.06
    НИ
    0.06
    HTTPHeader
    0.06
    XYZ
    0.06
    Act Density 0.048%

    No Known Activations