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

    Neuronpedia

    INDEX
    Explanations

    territory concerned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കലാ
    0.39
    ில்
    0.37
     송
    0.36
    ılık
    0.36
     और
    0.36
     de
    0.35
    ın
    0.35
    ის
    0.35
    ًا
    0.34
     मल्टी
    0.34
    POSITIVE LOGITS
     compd
    0.34
     saith
    0.34
     {}>,
    0.33
    땄
    0.31
     compds
    0.31
    ঠাৎ
    0.31
    റിന്റെ
    0.29
     pripad
    0.29
     valentines
    0.29
     pertain
    0.29
    Act Density 0.448%

    No Known Activations