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

    Neuronpedia

    INDEX
    Explanations

    tear or tears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    2.23
     وعند
    2.22
    десят
    2.22
    ter
    2.00
    ch
    1.78
    г
    1.76
    丆
    1.74
    preis
    1.73
    tes
    1.70
    ként
    1.69
    POSITIVE LOGITS
    ar
    2.31
     spacious
    2.16
    ू
    2.05
    ار
    1.99
    ל
    1.97
     totalitarian
    1.89
     keepsake
    1.89
     corvette
    1.86
     lẻ
    1.83
     flagship
    1.80
    Act Density 0.005%

    No Known Activations