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

    Neuronpedia

    INDEX
    Explanations

    heading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stabile
    -0.08
    plant
    -0.08
    ard
    -0.07
     varen
    -0.07
     mañana
    -0.07
     Reservoir
    -0.07
    habit
    -0.07
    ferred
    -0.07
    σκευ
    -0.07
     Pandora
    -0.07
    POSITIVE LOGITS
     headings
    0.11
     স্ত
    0.10
     hierarchy
    0.10
     제목
    0.09
    _heading
    0.09
     Heading
    0.09
     capitalization
    0.09
     一级
    0.09
    等级
    0.09
    .heading
    0.09
    Act Density 0.007%

    No Known Activations