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

    Neuronpedia

    INDEX
    Explanations

    even if / attempting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ाइज
    0.41
    យៈ
    0.39
     pelajar
    0.39
    រយៈពេល
    0.39
     dram
    0.39
    س
    0.38
     KIM
    0.38
     docente
    0.37
     turpis
    0.37
    实时
    0.37
    POSITIVE LOGITS
    Raises
    0.46
    Glor
    0.46
     उपर
    0.45
    쳐
    0.45
    Theme
    0.44
    Surname
    0.44
    WCHAR
    0.44
    Trou
    0.44
    Blessed
    0.43
     मुख
    0.43
    Act Density 0.002%

    No Known Activations