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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áze
    -0.08
     Incorpor
    -0.07
    458
    -0.06
    限定
    -0.06
    vh
    -0.06
     개인
    -0.06
     janvier
    -0.06
     winding
    -0.06
    rett
    -0.06
     QLD
    -0.06
    POSITIVE LOGITS
    iplina
    0.07
     serious
    0.06
     кора
    0.06
    (project
    0.06
     leash
    0.06
    .nn
    0.06
    &B
    0.06
     Caval
    0.06
     geb
    0.06
    ']")↵
    0.06
    Act Density 0.069%

    No Known Activations