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

    Neuronpedia

    INDEX
    Explanations

    political events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obtains
    -0.07
     شوند
    -0.06
     rewriting
    -0.06
    ("`
    -0.06
    chain
    -0.06
    lige
    -0.06
     nearer
    -0.06
     Champions
    -0.06
    (ValueError
    -0.06
    .HttpServletResponse
    -0.06
    POSITIVE LOGITS
     reasoned
    0.07
    ็ม
    0.07
     Прот
    0.07
    ="//
    0.06
    .her
    0.06
    ]**
    0.06
    UILabel
    0.06
     củ
    0.06
    <b
    0.06
    告
    0.06
    Act Density 0.026%

    No Known Activations