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

    Neuronpedia

    INDEX
    Explanations

    narrative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lety
    -0.07
     California
    -0.07
     programs
    -0.07
    _dbg
    -0.07
     математи
    -0.06
    Atlantic
    -0.06
     přísluš
    -0.06
    «
    -0.06
    California
    -0.06
     iframe
    -0.06
    POSITIVE LOGITS
    _navigation
    0.07
     bottleneck
    0.06
     gösterir
    0.06
     productive
    0.06
    يا
    0.06
    adients
    0.06
     quantity
    0.06
    ivos
    0.06
    NER
    0.05
     سن
    0.05
    Act Density 0.034%

    No Known Activations