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

    Neuronpedia

    INDEX
    Explanations

    there are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     there
    0.93
     nincs
    0.84
     इसका
    0.81
    து
    0.80
     nadie
    0.80
    there
    0.78
     it
    0.77
     two
    0.77
     какое
    0.73
     возникает
    0.72
    POSITIVE LOGITS
     are
    1.60
     were
    1.48
     jsou
    1.37
     ovat
    1.30
     são
    1.30
     هستند
    1.29
     sont
    1.28
    were
    1.24
     są
    1.23
     WERE
    1.19
    Act Density 0.072%

    No Known Activations