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

    Neuronpedia

    INDEX
    Explanations

    laws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    擒
    -0.08
     Leads
    -0.07
     Hentai
    -0.07
    眚
    -0.07
    ップ
    -0.07
     scare
    -0.07
     smell
    -0.07
    bounds
    -0.07
    嗽
    -0.07
    -lasting
    -0.07
    POSITIVE LOGITS
    🤳
    0.08
     //"
    0.08
    taxonomy
    0.07
    caffe
    0.07
     Recommended
    0.07
    满了
    0.07
    全世界
    0.07
     Department
    0.06
    .cuda
    0.06
     x
    0.06
    Act Density 0.006%

    No Known Activations