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

    Neuronpedia

    INDEX
    Explanations

    conversational questions and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.70
    м
    0.61
    સ
    0.56
    พลาด
    0.50
    SYSTEM
    0.48
    솝
    0.46
    "})
    0.46
    ER
    0.45
    ので
    0.45
    મ
    0.45
    POSITIVE LOGITS
     Timberwolves
    0.44
     ratt
    0.43
    tien
    0.43
    狠狠
    0.42
     veteran
    0.42
    pues
    0.42
     tailored
    0.41
     PCE
    0.41
     graduation
    0.41
     desempeño
    0.41
    Act Density 0.001%

    No Known Activations