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

    Neuronpedia

    INDEX
    Explanations

    number of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.90
    n
    0.71
    很高
    0.70
    О
    0.70
    la
    0.67
    وه
    0.67
    mu
    0.66
    上看
    0.66
     применя
    0.62
     reasonableness
    0.62
    POSITIVE LOGITS
    ים
    0.87
    ς
    0.70
    sight
    0.68
    eşit
    0.66
    們
    0.66
    slant
    0.66
     TRUE
    0.66
     Mga
    0.65
     Mares
    0.65
     Realtor
    0.64
    Act Density 0.281%

    No Known Activations