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

    Neuronpedia

    INDEX
    Explanations

    years, birth and death dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ode
    0.40
    ડ
    0.39
    í
    0.37
    ovll
    0.35
    αν
    0.34
     Thiết
    0.34
    寜
    0.34
     빨
    0.34
    izma
    0.34
    uild
    0.33
    POSITIVE LOGITS
     amore
    0.47
     cariño
    0.44
     beni
    0.43
     como
    0.42
     canonical
    0.41
     Gaussian
    0.41
    Gaussian
    0.41
     Gómez
    0.41
     impegno
    0.40
     fledgling
    0.40
    Act Density 0.002%

    No Known Activations