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
    ارا
    -0.07
    ン�
    -0.07
    ringe
    -0.07
     qs
    -0.06
    >$
    -0.06
    .running
    -0.06
    Arguments
    -0.06
     Mormons
    -0.06
    rün
    -0.06
    >();
    -0.06
    POSITIVE LOGITS
    点击
    0.06
    Viewport
    0.06
    ilha
    0.06
    .head
    0.06
    -uri
    0.06
     thrilling
    0.06
     transforming
    0.06
     portrait
    0.06
    trap
    0.06
     gain
    0.06
    Act Density 0.016%

    No Known Activations