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

    Neuronpedia

    INDEX
    Explanations

    Hindi language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एवं
    0.40
     ہے۔
    0.35
     ও
    0.33
    づ
    0.33
    akha
    0.33
     bądź
    0.33
    ᱚ
    0.32
     अथवा
    0.32
    acchi
    0.31
    ྵ
    0.31
    POSITIVE LOGITS
    いくつかの
    0.52
    それを
    0.52
    अपने
    0.48
     이러한
    0.47
     अपनी
    0.46
     इसके
    0.45
     প্রথমবারের
    0.45
    自分の
    0.45
     उन्हें
    0.43
    自己的
    0.43
    Act Density 0.005%

    No Known Activations