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

    Neuronpedia

    INDEX
    Explanations

    knock-knock jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EK
    0.54
    ناو
    0.52
     bah
    0.48
     cH
    0.48
     huwa
    0.48
     nád
    0.47
    PROCESSING
    0.47
    enemy
    0.46
    rán
    0.46
    rush
    0.46
    POSITIVE LOGITS
     Acids
    0.54
    ים
    0.51
    кость
    0.50
     Р
    0.50
    ルの
    0.49
    وں
    0.46
    ร
    0.46
    น
    0.45
     А
    0.43
     postulated
    0.43
    Act Density 0.000%

    No Known Activations