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

    Neuronpedia

    INDEX
    Explanations

    lesser general

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.51
    il
    0.50
    a
    0.46
    im
    0.44
    ᴀ
    0.43
    eer
    0.42
    ect
    0.42
    ects
    0.42
    ective
    0.40
    これは
    0.40
    POSITIVE LOGITS
     calcS
    0.50
    𝘨
    0.50
     eTo
    0.46
     impatience
    0.46
    ታ
    0.44
    gian
    0.43
    𝒗
    0.42
    𝑭
    0.42
    𝘷
    0.41
    хта
    0.41
    Act Density 0.003%

    No Known Activations