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

    Neuronpedia

    INDEX
    Explanations

    yoga poses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encounters
    -0.07
    roduction
    -0.07
    (at
    -0.07
    Alloc
    -0.07
    luví
    -0.07
    пион
    -0.07
     hiệu
    -0.06
    aco
    -0.06
     misunderstood
    -0.06
     Translator
    -0.06
    POSITIVE LOGITS
     zw
    0.07
    Whether
    0.07
    .transforms
    0.06
     coatings
    0.06
    人类
    0.06
     handleMessage
    0.06
     طی
    0.06
    (""
    0.06
     binnen
    0.06
    ={{↵
    0.06
    Act Density 0.008%

    No Known Activations