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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    纴
    -0.07
     полу
    -0.07
    oto
    -0.07
     mapping
    -0.07
    رق
    -0.06
    报销
    -0.06
    修饰
    -0.06
     PRODUCTS
    -0.06
    .leading
    -0.06
     petits
    -0.06
    POSITIVE LOGITS
    黑龙江
    0.08
    _Local
    0.08
     Checks
    0.08
     rahats
    0.07
     vulnerabilities
    0.07
     lineage
    0.07
     kvinner
    0.07
    机会
    0.07
    (VALUE
    0.07
    ibration
    0.07
    Act Density 0.007%

    No Known Activations