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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eline
    -0.07
    kernel
    -0.07
    edl
    -0.07
     tabs
    -0.07
    jav
    -0.06
    ula
    -0.06
    nout
    -0.06
     Seal
    -0.06
     challenged
    -0.06
     Иванов
    -0.06
    POSITIVE LOGITS
     双线
    0.06
    (Size
    0.06
    价值
    0.06
    .mj
    0.06
     exclus
    0.06
    Anonymous
    0.06
     وهي
    0.06
     ))}↵
    0.06
     vap
    0.06
    /off
    0.06
    Act Density 0.096%

    No Known Activations