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

    Neuronpedia

    INDEX
    Explanations

    typescript interface declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thousand
    1.07
    ्स
    1.04
    داری
    1.01
    entire
    0.96
    धानी
    0.96
    ేక
    0.96
    sides
    0.93
     puas
    0.93
    Hospital
    0.93
    UTF
    0.92
    POSITIVE LOGITS
    >`,
    1.19
     danneggi
    1.16
     څنګه
    1.14
    ោម
    1.14
     accused
    1.14
     tablespoon
    1.12
     সীমা
    1.11
     lateinit
    1.11
    apabb
    1.07
    ंसिल
    1.07
    Act Density 0.037%

    No Known Activations