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

    Neuronpedia

    INDEX
    Explanations

    URLs and DOIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    0.71
     relazione
    0.58
    संबंध
    0.57
     In
    0.56
     Pendant
    0.56
    in
    0.55
     Related
    0.55
     Sunlight
    0.54
    ंसारी
    0.54
     Για
    0.53
    POSITIVE LOGITS
    "
    0.66
     g
    0.56
    ब
    0.53
     time
    0.52
     slavery
    0.52
     enem
    0.51
    惮
    0.51
    Time
    0.50
    Cread
    0.50
    گ
    0.50
    Act Density 0.013%

    No Known Activations