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

    Neuronpedia

    INDEX
    Explanations

    connection with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంచరీలు
    0.69
    માંથી
    0.47
    టమి
    0.47
     medan
    0.46
    为例
    0.46
     waarin
    0.44
    においては
    0.40
     dépour
    0.38
    ੋਂ
    0.38
    ிலிருந்து
    0.37
    POSITIVE LOGITS
     with
    3.34
     avec
    3.08
     với
    3.03
    with
    2.95
     dengan
    2.95
     עם
    2.92
    กับ
    2.75
    dengan
    2.47
     WITH
    2.42
     със
    2.41
    Act Density 0.911%

    No Known Activations