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

    Neuronpedia

    INDEX
    Explanations

    simply, about, critical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mailing
    0.46
    laat
    0.45
    being
    0.44
    been
    0.41
    運
    0.41
    Sam
    0.41
    ool
    0.40
    into
    0.39
    keys
    0.39
    iche
    0.39
    POSITIVE LOGITS
     điện
    0.48
     disapproved
    0.46
     miniatur
    0.45
     식품
    0.44
     disini
    0.44
    विटी
    0.44
    িগ
    0.43
    Foldout
    0.43
     çünkü
    0.43
     sucked
    0.42
    Act Density 0.000%

    No Known Activations