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

    Neuronpedia

    INDEX
    Explanations

    time spent or it takes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    価格
    0.45
     страны
    0.45
    ри
    0.44
    Ма
    0.44
    午後
    0.44
     значение
    0.43
    Си
    0.43
    స్
    0.43
    Х
    0.43
    the
    0.43
    POSITIVE LOGITS
     用于
    0.49
     teething
    0.48
     disrupts
    0.46
     therapies
    0.44
     medically
    0.44
     ways
    0.44
     በሽታ
    0.44
     interruption
    0.44
     teasing
    0.43
    蔫
    0.43
    Act Density 0.013%

    No Known Activations