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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detection
    -0.08
     Detection
    -0.07
     lane
    -0.06
     verwenden
    -0.06
     ding
    -0.06
     speculation
    -0.06
     freeze
    -0.06
    альна
    -0.06
     type
    -0.06
    -powered
    -0.06
    POSITIVE LOGITS
     tamamen
    0.06
     зовсім
    0.06
    endsWith
    0.06
    icits
    0.06
    阪
    0.06
    �
    0.06
     differs
    0.06
    .getcwd
    0.06
    iffer
    0.06
     Merkez
    0.06
    Act Density 0.263%

    No Known Activations