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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEFINED
    -0.10
     বাদ
    -0.09
    recursive
    -0.08
    ged
    -0.08
    pointer
    -0.08
     recursive
    -0.08
    (src
    -0.08
     भाई
    -0.07
     Vere
    -0.07
    mapped
    -0.07
    POSITIVE LOGITS
     staff
    0.07
     personnel
    0.07
    |()↵
    0.07
    分
    0.07
     fitting
    0.07
    特码
    0.07
    服务热线
    0.07
    摘要
    0.07
     police
    0.07
     guiding
    0.07
    Act Density 0.001%

    No Known Activations