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

    Neuronpedia

    INDEX
    Explanations

    "range and count"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tắt
    1.38
     xong
    1.37
    બ
    1.36
     Orbit
    1.34
     stap
    1.34
    asmuch
    1.33
     ایت
    1.32
    שהו
    1.30
     właśnie
    1.28
     páginas
    1.27
    POSITIVE LOGITS
    Factors
    1.70
    instances
    1.59
    ვნ
    1.57
    𝖊
    1.54
    OrDefault
    1.53
    xq
    1.52
    грани
    1.49
    ки
    1.47
    িদের
    1.47
     factors
    1.47
    Act Density 0.000%

    No Known Activations