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

    Neuronpedia

    INDEX
    Explanations

    numbers and currency or units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丵
    0.30
    सेज
    0.26
    ूहिक
    0.25
     categorically
    0.25
    잖아요
    0.24
     وګټ
    0.23
     Biom
    0.23
     नौकर
    0.23
    کروچ
    0.22
    <unused1032>
    0.22
    POSITIVE LOGITS
    5
    0.27
    8
    0.26
    7
    0.26
     וח
    0.25
    6
    0.25
    0.25
     ونص
    0.25
     ¾
    0.24
    ½
    0.24
    ¾
    0.23
    Act Density 0.258%

    No Known Activations