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

    Neuronpedia

    INDEX
    Explanations

    Interviewers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATS
    -0.08
     تل
    -0.07
     mutant
    -0.07
     liên
    -0.07
     هند
    -0.07
     ร
    -0.06
    �
    -0.06
     MI
    -0.06
     miễn
    -0.06
    麻
    -0.06
    POSITIVE LOGITS
    料理
    0.07
    PointerType
    0.06
    stell
    0.06
    なる
    0.06
     kullanım
    0.06
    iểu
    0.06
     '-')
    0.06
    __/
    0.06
    Fed
    0.06
    ="(
    0.06
    Act Density 0.008%

    No Known Activations