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
     p
    -0.08
     horizon
    -0.07
     SPR
    -0.07
    p
    -0.07
    。<
    -0.06
     P
    -0.06
    直接
    -0.06
     leap
    -0.06
    .XtraLayout
    -0.06
    完整
    -0.06
    POSITIVE LOGITS
    ubble
    0.07
     poisonous
    0.07
    <Employee
    0.07
    .sky
    0.06
     ngủ
    0.06
    ière
    0.06
     babel
    0.06
     resemble
    0.06
    Detection
    0.06
    Curr
    0.06
    Act Density 0.000%

    No Known Activations