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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    för
    -0.06
     Shelter
    -0.06
    hores
    -0.06
     preceding
    -0.06
     unacceptable
    -0.06
    ø
    -0.06
     roofs
    -0.06
    不同的
    -0.06
    nul
    -0.06
    POSITIVE LOGITS
    .Enabled
    0.07
    千
    0.07
     transformations
    0.07
     studying
    0.06
    |i
    0.06
    _driver
    0.06
    /releases
    0.06
     leben
    0.06
    기타
    0.06
    Edition
    0.06
    Act Density 0.003%

    No Known Activations