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

    Neuronpedia

    INDEX
    Explanations

    technical/academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dots
    -0.07
    .UTF
    -0.07
    Як
    -0.07
     Μ
    -0.06
     gerekli
    -0.06
    оваться
    -0.06
     geg
    -0.06
     hope
    -0.06
     hopes
    -0.06
    Forum
    -0.06
    POSITIVE LOGITS
    _country
    0.07
     """↵↵
    0.06
    loud
    0.06
    ,b
    0.06
     Brian
    0.06
    conomics
    0.06
    ucas
    0.06
     Poison
    0.06
     assass
    0.06
     Alberta
    0.06
    Act Density 0.424%

    No Known Activations