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

    Neuronpedia

    INDEX
    Explanations

    window seat, aisle seat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dl
    0.54
    up
    0.50
     to
    0.50
    Answer
    0.49
    বাই
    0.49
    ሠራ
    0.49
    ujących
    0.48
    Story
    0.48
    Take
    0.47
    rn
    0.46
    POSITIVE LOGITS
     henna
    0.57
     खेतों
    0.52
     गांव
    0.51
     hambre
    0.50
     caderno
    0.49
     ovip
    0.49
     poodle
    0.48
     Madonna
    0.48
    铷
    0.47
    డా
    0.47
    Act Density 0.000%

    No Known Activations