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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    המל
    -0.07
     rsa
    -0.07
    �
    -0.07
     tribe
    -0.07
     forte
    -0.07
     а
    -0.07
    　　
    -0.07
     mga
    -0.06
    また
    -0.06
    brtc
    -0.06
    POSITIVE LOGITS
     scrapped
    0.07
    下沉
    0.07
     lowers
    0.07
    وال
    0.07
     Hopkins
    0.07
     Go
    0.07
     Wrong
    0.07
    -live
    0.07
     SCREEN
    0.07
    习惯了
    0.07
    Act Density 0.002%

    No Known Activations