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

    Neuronpedia

    INDEX
    Explanations

    denominator and bottom number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tetap
    0.47
     vorbere
    0.47
     teljes
    0.46
     starten
    0.46
     préparation
    0.46
     použ
    0.44
     continúa
    0.44
     beim
    0.44
    ियोग्राफी
    0.43
     intend
    0.43
    POSITIVE LOGITS
     Wissenschaften
    0.42
    俱乐
    0.42
    วั
    0.39
     Architectural
    0.39
    ല്ലാ
    0.38
     насеко
    0.38
    基础设施
    0.37
     તરી
    0.36
    らった
    0.36
     Massachusetts
    0.36
    Act Density 0.001%

    No Known Activations