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

    Neuronpedia

    INDEX
    Explanations

    contractual agreements and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    했다
    0.50
     modestly
    0.49
    뱀
    0.48
    <0xA1>
    0.48
    ကုန်
    0.48
    umerate
    0.48
     intento
    0.48
    гле
    0.47
    满意
    0.47
    оте
    0.47
    POSITIVE LOGITS
     Six
    0.48
     En
    0.47
     Days
    0.47
     Comp
    0.47
     Agreements
    0.46
     Ent
    0.46
     शर्तों
    0.46
     Time
    0.46
     Crush
    0.46
     Okay
    0.45
    Act Density 0.001%

    No Known Activations