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

    Neuronpedia

    INDEX
    Explanations

    names like Bill Smith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الشركات
    0.46
     tribun
    0.40
    INVEST
    0.38
     законода
    0.38
     bedrijven
    0.38
    企业
    0.38
     स्वाद
    0.36
    廉
    0.36
     Carolyn
    0.36
     ADMINISTR
    0.36
    POSITIVE LOGITS
    ose
    0.39
     due
    0.39
     imported
    0.39
    &=
    0.39
     compound
    0.38
    bild
    0.38
     Default
    0.37
     negative
    0.37
    omorphism
    0.37
    coll
    0.36
    Act Density 0.010%

    No Known Activations