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

    Neuronpedia

    INDEX
    Explanations

    sequence structure or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ద్ద
    0.48
    瀆
    0.47
    iless
    0.46
    atility
    0.46
     worldRank
    0.46
    สห
    0.45
     xas
    0.44
     მიმოწერა
    0.44
     Withers
    0.44
    mniej
    0.43
    POSITIVE LOGITS
    ,
    0.52
     échant
    0.46
     garantiert
    0.46
     assicur
    0.46
     conformation
    0.45
     increíble
    0.45
     échantillons
    0.44
     vielleicht
    0.44
     OC
    0.43
     B
    0.42
    Act Density 0.005%

    No Known Activations