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

    Neuronpedia

    INDEX
    Explanations

    as the crow flies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    γου
    0.41
    𝜃
    0.40
    ϴ
    0.39
    ρον
    0.37
    িপ
    0.37
     acet
    0.35
    シック
    0.35
    苎
    0.35
    Stroke
    0.34
    iligung
    0.34
    POSITIVE LOGITS
     flying
    4.16
     fly
    3.77
     Flying
    3.63
    Flying
    3.63
    flying
    3.61
    飞
    3.61
    飛
    3.58
     flew
    3.50
     FLY
    3.38
     Fly
    3.33
    Act Density 0.060%

    No Known Activations