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

    Neuronpedia

    INDEX
    Explanations

    Okay, how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    courses
    0.85
    +:
    0.79
    ():
    0.79
     noteworthy
    0.78
     হিসাবে
    0.78
    ckså
    0.76
     muchísimo
    0.76
    descriptions
    0.74
     notable
    0.74
    academic
    0.74
    POSITIVE LOGITS
    etele
    0.82
    能否
    0.81
     Rotate
    0.80
     Cannot
    0.77
    ालय
    0.74
     공유
    0.73
     Sharing
    0.73
     Aktual
    0.70
     आप
    0.69
     conflitto
    0.69
    Act Density 0.128%

    No Known Activations