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

    Neuronpedia

    INDEX
    Explanations

    better than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.99
    sville
    1.77
    si
    1.64
    m
    1.59
    ses
    1.55
    suz
    1.54
    sen
    1.52
    sd
    1.52
    sg
    1.49
    sv
    1.45
    POSITIVE LOGITS
     than
    1.98
    Than
    1.73
     niż
    1.73
    械
    1.62
     decât
    1.59
     än
    1.56
     Than
    1.53
     kuin
    1.50
     THAN
    1.47
    than
    1.40
    Act Density 0.474%

    No Known Activations