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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation context indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ومات
    0.34
     бушлай
    0.33
    اونلو
    0.31
    掮
    0.31
    Fiscal
    0.30
    饷
    0.30
    WMat
    0.30
    膂
    0.30
    दिग्ध
    0.29
    Despatx
    0.29
    POSITIVE LOGITS
     =
    0.44
     .
    0.38
    '
    0.38
     ,
    0.36
    z
    0.34
    ↵↵
    0.34
    .
    0.34
    ,
    0.34
    ’
    0.34
    \
    0.33
    Act Density 0.128%

    No Known Activations