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

    Neuronpedia

    INDEX
    Explanations

    lists of data and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anastomosis
    0.61
     новом
    0.57
     Yeni
    0.56
     comenzar
    0.55
     ignited
    0.54
     அற்புதமான
    0.54
     anastom
    0.54
     secrete
    0.54
     fotografías
    0.52
     заповед
    0.51
    POSITIVE LOGITS
    (
    0.57
    ’
    0.49
    App
    0.49
    Con
    0.48
    會
    0.47
    Fl
    0.46
    Nord
    0.45
    Fil
    0.45
    ↵↵
    0.42
    <0xEF>
    0.42
    Act Density 0.000%

    No Known Activations