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

    Neuronpedia

    INDEX
    Explanations

    Intel products and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ON
    0.82
     year
    0.61
    ki
    0.61
    life
    0.60
     இருக்கும்
    0.60
    year
    0.59
    Brewer
    0.59
    ching
    0.59
    Wor
    0.59
     continue
    0.59
    POSITIVE LOGITS
    ด
    0.71
    ้
    0.68
    َال
    0.65
    раз
    0.64
     épais
    0.63
    те
    0.63
    տ
    0.62
    д
    0.60
    ри
    0.59
     résult
    0.59
    Act Density 0.020%

    No Known Activations