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

    Neuronpedia

    INDEX
    Explanations

    on the one hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     También
    0.46
     भी
    0.45
     بھی
    0.44
     أيضا
    0.43
     ايضا
    0.43
    也會
    0.42
    to
    0.42
    也可以
    0.42
     też
    0.42
     nhiều
    0.41
    POSITIVE LOGITS
     ketchup
    0.42
    <0x0D>
    0.42
    係
    0.40
     sincere
    0.38
     IBOutlet
    0.38
     moistur
    0.38
     serde
    0.38
     glomer
    0.37
    rogation
    0.37
    精致
    0.37
    Act Density 0.008%

    No Known Activations