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

    Neuronpedia

    INDEX
    Explanations

    non-binary classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pleas
    0.56
    သော
    0.53
     wenige
    0.50
     Surrounded
    0.50
    示した
    0.48
     Kettle
    0.48
     Obrigado
    0.48
     いや
    0.47
    ઈએ
    0.47
     Both
    0.47
    POSITIVE LOGITS
     components
    0.52
     organisms
    0.52
     insects
    0.51
     basics
    0.50
    ové
    0.50
     pollutants
    0.48
     pests
    0.47
     organism
    0.47
    /
    0.46
     interlocking
    0.46
    Act Density 0.605%

    No Known Activations