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

    Neuronpedia

    INDEX
    Explanations

    Sports standings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yayım
    -0.07
    eniz
    -0.06
    -vars
    -0.06
     bais
    -0.06
     Nil
    -0.06
     Village
    -0.06
    ponential
    -0.06
    
↵

↵
    -0.06
     Fried
    -0.06
     mean
    -0.06
    POSITIVE LOGITS
    ешь
    0.07
    dealloc
    0.07
     точки
    0.07
     rè
    0.07
    iah
    0.07
    터
    0.06
     playground
    0.06
     звичай
    0.06
    .Inventory
    0.06
    衣服
    0.06
    Act Density 0.040%

    No Known Activations