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

    Neuronpedia

    INDEX
    Explanations

    a/an/as/of/for/having + adjective/noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    der
    0.90
    bil
    0.83
    ov
    0.82
    omp
    0.82
    had
    0.82
    ca
    0.80
    "><?=$
    0.80
    definite
    0.80
    ">(</
    0.79
    cal
    0.78
    POSITIVE LOGITS
     nomads
    0.93
     Engines
    0.89
     unitarity
    0.87
     Только
    0.87
     oamenii
    0.86
     войск
    0.86
    ਉ
    0.86
     그룹
    0.85
    лянчук
    0.84
    ੀਆਂ
    0.84
    Act Density 0.000%

    No Known Activations