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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adapters
    -0.08
    thumb
    -0.07
     месте
    -0.06
     urn
    -0.06
    ера
    -0.06
     overwhelmed
    -0.06
     cle
    -0.06
     territory
    -0.06
    'elle
    -0.06
     expended
    -0.06
    POSITIVE LOGITS
     боль
    0.06
    ดวก
    0.06
     şimdi
    0.06
     Semaphore
    0.06
    Jake
    0.06
     unmatched
    0.06
    .Authentication
    0.06
     ev
    0.06
    :UI
    0.06
    ınızı
    0.06
    Act Density 0.020%

    No Known Activations