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

    Neuronpedia

    INDEX
    Explanations

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ృష్టి
    0.40
     gestern
    0.35
    ప్పుడు
    0.33
     quiera
    0.33
     Перейти
    0.32
     ہوں۔
    0.32
     NSLog
    0.32
    গত
    0.32
     raconte
    0.31
    包含了
    0.30
    POSITIVE LOGITS
     with
    0.56
    with
    0.50
     עם
    0.49
     via
    0.46
     với
    0.46
     dengan
    0.45
    With
    0.44
     under
    0.44
     în
    0.44
    9
    0.43
    Act Density 0.042%

    No Known Activations