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

    Neuronpedia

    INDEX
    Explanations

    reading comprehension

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     striving
    -0.07
     persuasion
    -0.07
    	input
    -0.06
     servings
    -0.06
    mem
    -0.06
    _contains
    -0.06
    森
    -0.06
     spaces
    -0.06
     write
    -0.06
     Tip
    -0.06
    POSITIVE LOGITS
     Peter
    0.07
    "^
    0.07
    immel
    0.06
     соот
    0.06
    ушки
    0.06
    ToFront
    0.06
     Serif
    0.06
    年龄
    0.06
    กล
    0.06
     комплекс
    0.06
    Act Density 0.052%

    No Known Activations