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

    Neuronpedia

    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    知晓
    -0.09
     Persian
    -0.08
    賺
    -0.07
    .neg
    -0.07
     ACCESS
    -0.07
     lagi
    -0.07
    […
    -0.07
    (period
    -0.07
     Interstate
    -0.07
    作者
    -0.07
    POSITIVE LOGITS
                                 ↵
    0.08
    莿
    0.07
    🇧
    0.07
    なかった
    0.07
     statue
    0.07
    选
    0.07
    缩
    0.07
    构
    0.07
     supporting
    0.07
    -----------
↵
    0.07
    Act Density 0.045%

    No Known Activations