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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     która
    0.53
     että
    0.52
     który
    0.51
     هایی
    0.50
    릎
    0.50
    㳡
    0.49
     którzy
    0.49
     kteří
    0.45
    ‌هایی
    0.45
    ృష్
    0.45
    POSITIVE LOGITS
     oraz
    0.53
     including
    0.51
    ,
    0.50
     invariably
    0.50
     INCLUDING
    0.48
    ،
    0.46
    including
    0.46
    Ñ
    0.46
     dearly
    0.46
     ביותר
    0.45
    Act Density 0.602%

    No Known Activations