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

    Neuronpedia

    INDEX
    Explanations

    absence or negation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ros
    0.43
     React
    0.42
    React
    0.41
    REACT
    0.39
     REACT
    0.39
    Iso
    0.39
    Merci
    0.38
     lalu
    0.38
     мер
    0.38
     येत
    0.38
    POSITIVE LOGITS
     no
    0.58
    naming
    0.48
     naming
    0.47
     ordered
    0.46
    no
    0.44
     ban
    0.42
     ordering
    0.42
     Order
    0.39
     Ordered
    0.39
     indent
    0.38
    Act Density 0.000%

    No Known Activations