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

    Neuronpedia

    INDEX
    Explanations

    temperature between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     savings
    0.45
     severally
    0.44
     >=
    0.43
     micron
    0.42
     bokeh
    0.41
     zyg
    0.41
     repetition
    0.41
     <=
    0.41
     satur
    0.40
     halftime
    0.40
    POSITIVE LOGITS
     armchair
    0.47
     எதுவும்
    0.46
     அனுப்பி
    0.46
     ສ
    0.46
     Instinct
    0.45
    นี้
    0.44
    oit
    0.44
     অস্ত্র
    0.44
     চারটি
    0.44
     ingeniero
    0.43
    Act Density 0.007%

    No Known Activations