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

    Neuronpedia

    INDEX
    Explanations

    pseudocode or gherkin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ہ
    1.11
    time
    1.04
    ลล์
    1.00
    il
    0.97
    to
    0.95
    Ridge
    0.91
     mano
    0.90
    ttt
    0.90
    toon
    0.90
    tennis
    0.89
    POSITIVE LOGITS
     مفه
    0.97
     zumindest
    0.91
    ниями
    0.88
    bx
    0.88
    ettha
    0.87
    यां
    0.86
     appellees
    0.86
    ycznej
    0.85
    STRAINT
    0.84
    dorf
    0.84
    Act Density 0.006%

    No Known Activations