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

    Neuronpedia

    INDEX
    Explanations

    spicy, frictionless, Brazilian, operative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yl
    0.57
    jaro
    0.54
    非常
    0.52
    ing
    0.51
    ad
    0.51
    Y
    0.51
    ia
    0.50
    enson
    0.50
     premieres
    0.50
    san
    0.50
    POSITIVE LOGITS
     কিছুটা
    0.47
    Buildings
    0.47
     proizvoda
    0.47
    Clothing
    0.46
    зу
    0.46
    chandise
    0.46
    ি
    0.45
    盂
    0.45
    ності
    0.45
    зок
    0.45
    Act Density 0.000%

    No Known Activations