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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Birch
    -0.07
     tasks
    -0.07
     ultra
    -0.07
     ان
    -0.06
     tf
    -0.06
     пенси
    -0.06
     Electrical
    -0.06
    🏤
    -0.06
    nü
    -0.06
    POSITIVE LOGITS
     retali
    0.09
    ornecedor
    0.07
    ]+\
    0.07
    并于
    0.07
     squat
    0.07
    索赔
    0.07
    דרך
    0.07
    RequestId
    0.07
    thanks
    0.06
     DateFormatter
    0.06
    Act Density 0.001%

    No Known Activations