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

    Neuronpedia

    INDEX
    Explanations

    question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xcodeproj
    1.12
     pompa
    1.08
     bastante
    1.08
     démar
    1.08
     gewisse
    1.06
    Deadline
    1.06
     belirli
    1.04
     previsão
    1.03
    ímos
    1.03
     bizony
    1.03
    POSITIVE LOGITS
     Yates
    1.03
    HAND
    1.00
     ذ
    0.97
     Inglis
    0.96
     Gill
    0.96
     ен
    0.94
     WEB
    0.93
     ي
    0.93
     وب
    0.93
    倌
    0.91
    Act Density 0.076%

    No Known Activations