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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     заб
    -0.07
    센터
    -0.06
     lr
    -0.06
     عب
    -0.06
    <Sprite
    -0.06
    なんて
    -0.05
     CType
    -0.05
     toes
    -0.05
     apellido
    -0.05
     запит
    -0.05
    POSITIVE LOGITS
     comparative
    0.07
     sessionId
    0.07
    ンダ
    0.07
     Station
    0.07
     slash
    0.06
    LIB
    0.06
    转
    0.06
     سان
    0.06
     مختلف
    0.06
    ال
    0.06
    Act Density 0.001%

    No Known Activations