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

    Neuronpedia

    INDEX
    Explanations

    El

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fueled
    0.46
    िएगा
    0.46
    uid
    0.45
    暂停
    0.45
    வர்
    0.45
    betriebnahme
    0.44
     sự
    0.43
    ructor
    0.43
     структур
    0.42
    ihl
    0.42
    POSITIVE LOGITS
    ཱ
    0.49
     ہیں۔
    0.41
     linguistics
    0.41
     piccoli
    0.41
    kka
    0.40
     cercare
    0.40
     educación
    0.39
    るので
    0.39
    кме
    0.39
     recherche
    0.39
    Act Density 0.002%

    No Known Activations