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

    Neuronpedia

    INDEX
    Explanations

    Dissolving materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sl
    -0.07
    frage
    -0.07
    CellValue
    -0.07
    Fil
    -0.06
    arges
    -0.06
    bar
    -0.06
    /Area
    -0.06
     obedient
    -0.06
    封
    -0.06
    olu
    -0.06
    POSITIVE LOGITS
    άρ
    0.07
     structured
    0.06
     Ethiopia
    0.06
     أمريكي
    0.06
     BUY
    0.06
     brought
    0.06
    ROUTE
    0.06
     serialized
    0.06
    weather
    0.06
     гиб
    0.06
    Act Density 0.019%

    No Known Activations