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

    Neuronpedia

    INDEX
    Explanations

    technical/programming text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parseInt
    -0.07
     TestUtils
    -0.07
     Metrics
    -0.07
     filePath
    -0.07
     safezone
    -0.07
     productName
    -0.07
     Les
    -0.07
     Dialogue
    -0.07
     palabras
    -0.07
    motion
    -0.06
    POSITIVE LOGITS
    -II
    0.06
     qt
    0.06
     bestellen
    0.06
    paired
    0.06
    也有
    0.06
    MIT
    0.06
    리
    0.06
    лок
    0.06
     anzeigen
    0.06
    ап
    0.06
    Act Density 0.089%

    No Known Activations