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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    牧
    -0.06
    /bar
    -0.06
    Gratis
    -0.06
     prat
    -0.06
    ulado
    -0.06
     dining
    -0.06
     youths
    -0.06
     rehab
    -0.06
    Bars
    -0.06
    <|start_header_id|>
    -0.06
    POSITIVE LOGITS
     vex
    0.07
     Academ
    0.06
    вы
    0.06
    恒
    0.06
    CppCodeGen
    0.06
     compulsory
    0.06
    enberg
    0.06
    віт
    0.06
    ↵↵↵↵↵↵
    0.06
    <Article
    0.06
    Act Density 0.029%

    No Known Activations