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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owards
    -0.08
     corner
    -0.07
     Courier
    -0.07
    >\↵
    -0.07
     buyer
    -0.07
    ([(
    -0.07
    idges
    -0.07
    斐
    -0.07
    �
    -0.06
    絮
    -0.06
    POSITIVE LOGITS
     הרכב
    0.08
     Belgi
    0.08
     timespec
    0.07
    苈
    0.07
    蒎
    0.07
    荭
    0.07
    👕
    0.07
     hang
    0.07
     horrend
    0.07
     eğer
    0.07
    Act Density 0.009%

    No Known Activations