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

    Neuronpedia

    INDEX
    Explanations

    Pop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    วโม
    -0.07
    (Project
    -0.07
     учрежд
    -0.06
    istringstream
    -0.06
    被
    -0.06
     обрат
    -0.06
    LTR
    -0.06
    某
    -0.06
    浦
    -0.06
    628
    -0.06
    POSITIVE LOGITS
     Presented
    0.07
    express
    0.07
    itemap
    0.07
    ..↵
    0.06
    .
↵
    0.06
     Jerseys
    0.06
    :expr
    0.06
     مقابل
    0.06
    得
    0.06
     عرض
    0.06
    Act Density 0.001%

    No Known Activations