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

    Neuronpedia

    INDEX
    Explanations

    expectations vs reality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destacado
    -0.07
     rocking
    -0.07
    طقة
    -0.07
     Uiteindelijk
    -0.07
     disputed
    -0.07
    ющихся
    -0.07
    loč
    -0.07
    ล่าสุด
    -0.07
    (timestamp
    -0.07
    ישים
    -0.07
    POSITIVE LOGITS
    期待
    0.16
     expecting
    0.16
     기대
    0.15
     توقع
    0.15
     forvent
    0.15
     oček
    0.15
     erwartet
    0.15
     ожид
    0.14
     expectations
    0.14
     expects
    0.14
    Act Density 0.065%

    No Known Activations