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

    Neuronpedia

    INDEX
    Explanations

    mentioning specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Determine
    0.66
     Demonstrated
    0.58
     Understanding
    0.55
     demonstrated
    0.55
     Determining
    0.52
     för
    0.51
     Defender
    0.51
    𝟎
    0.51
     для
    0.50
    ۔
    0.50
    POSITIVE LOGITS
    t
    0.79
     erwäh
    0.72
     erwähnt
    0.69
     mention
    0.67
    Mention
    0.66
    提到的
    0.66
    К
    0.63
    mention
    0.61
    m
    0.60
     mencion
    0.60
    Act Density 0.046%

    No Known Activations