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

    Neuronpedia

    INDEX
    Explanations

    multilingual conjunctions and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.89
    I
    0.72
     A
    0.65
    matic
    0.61
    s
    0.58
    ses
    0.57
     Database
    0.55
    sman
    0.52
    In
    0.50
     That
    0.50
    POSITIVE LOGITS
     và
    0.97
     و
    0.95
     και
    0.95
     и
    0.92
     gebruiken
    0.88
     facteurs
    0.84
    ة
    0.83
     milliers
    0.83
     traitement
    0.81
     funziona
    0.81
    Act Density 0.311%

    No Known Activations