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

    Neuronpedia

    INDEX
    Explanations

    internal state, functions, calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    牷
    0.51
    щик
    0.50
    AdType
    0.49
    SCHRAMM
    0.49
    ஸ்தான
    0.47
     ዓይነ
    0.47
    בּ
    0.47
    軗
    0.46
    刬
    0.45
    癃
    0.44
    POSITIVE LOGITS
     include
    0.43
    tilde
    0.42
     diverse
    0.41
     year
    0.40
     consortium
    0.40
    itere
    0.40
    itim
    0.40
     collaborative
    0.39
     un
    0.38
    onia
    0.38
    Act Density 0.003%

    No Known Activations