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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hika
    0.46
     နောက်
    0.41
    悗
    0.41
     左
    0.40
     もう
    0.40
    ופי
    0.39
    ορ
    0.39
     ಅದನ್ನು
    0.39
    ᓕ
    0.38
     Another
    0.38
    POSITIVE LOGITS
    それぞれ
    0.56
     entrambi
    0.51
     respectivement
    0.49
     keduanya
    0.48
     respectively
    0.47
     these
    0.47
    これらの
    0.47
    这两个
    0.47
     bunlar
    0.47
     begge
    0.47
    Act Density 0.076%

    No Known Activations