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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shapes
    -0.08
    不是一个
    -0.07
    _ht
    -0.07
    YLeaf
    -0.07
    =head
    -0.07
     Subset
    -0.07
    ]==
    -0.07
     nerve
    -0.07
    .*?)
    -0.07
     wiped
    -0.07
    POSITIVE LOGITS
     مهم
    0.08
    ಲ
    0.07
    оро
    0.07
     vít
    0.07
     la
    0.07
     hẳ
    0.07
    嘀
    0.07
    isseur
    0.06
     fully
    0.06
    ביע
    0.06
    Act Density 0.072%

    No Known Activations