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

    Neuronpedia

    INDEX
    Explanations

    mathematical solutions or conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dan
    0.68
    Alongside
    0.66
     alongside
    0.66
    と共に
    0.63
    times
    0.62
    eman
    0.61
    ctime
    0.61
     accompany
    0.61
    中に
    0.59
    include
    0.59
    POSITIVE LOGITS
     Therefore
    1.02
     Vậy
    0.95
     jadi
    0.95
     Portanto
    0.95
     Hence
    0.93
     somit
    0.89
     !!!
    0.88
     voilà
    0.88
     portanto
    0.87
     Jadi
    0.86
    Act Density 0.828%

    No Known Activations