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

    Neuronpedia

    INDEX
    Explanations

    izers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alamat
    -0.07
    anlık
    -0.07
     phenomena
    -0.07
    hel
    -0.07
     han
    -0.06
    .Timestamp
    -0.06
     SL
    -0.06
    helm
    -0.06
    111
    -0.06
    atı
    -0.06
    POSITIVE LOGITS
     fertilizer
    0.08
    inery
    0.07
    덤프
    0.07
     Purdue
    0.06
    izers
    0.06
     shortage
    0.06
     isVisible
    0.06
    viewController
    0.06
    .Feed
    0.06
     kullanılır
    0.06
    Act Density 0.001%

    No Known Activations