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

    Neuronpedia

    INDEX
    Explanations

    slight differences and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tussen
    1.06
     between
    1.06
     BETWEEN
    0.98
     mellan
    0.96
     між
    0.95
    between
    0.95
     između
    0.94
     Between
    0.89
     mellem
    0.89
     antara
    0.87
    POSITIVE LOGITS
     differing
    2.04
     unterschied
    1.98
     differently
    1.92
     unterschiedlich
    1.89
     varying
    1.89
    Different
    1.79
     different
    1.75
     Different
    1.75
     differ
    1.74
     വ്യത്യസ്ത
    1.66
    Act Density 0.353%

    No Known Activations