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

    Neuronpedia

    INDEX
    Explanations

    Excellent, health, confession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patent
    0.46
    patent
    0.45
     Patent
    0.42
    (",");
    0.41
    YE
    0.40
     Munich
    0.38
    arder
    0.38
     patente
    0.38
     PATENT
    0.37
    Patent
    0.37
    POSITIVE LOGITS
    㞱
    0.45
    reibung
    0.44
    的任务
    0.44
     descon
    0.40
    ieken
    0.39
    lacht
    0.39
    保养
    0.39
     kıs
    0.38
     nCount
    0.38
    ໌
    0.38
    Act Density 0.000%

    No Known Activations