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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    যায়
    0.43
    ग्रह
    0.37
     ваших
    0.37
    ريقه
    0.37
    ाइब
    0.35
     bismuth
    0.35
    ॅमिली
    0.35
     amyl
    0.35
     знаем
    0.34
     subscripts
    0.34
    POSITIVE LOGITS
     Changel
    0.38
    aught
    0.36
     {{
    0.35
    '`
    0.35
    ydon
    0.34
     Trad
    0.34
    uddersfield
    0.33
    ória
    0.33
    áh
    0.33
    srt
    0.33
    Act Density 0.098%

    No Known Activations