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

    Neuronpedia

    INDEX
    Explanations

    you would like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.77
    OGLYPH
    -0.77
    ▏
    -0.75
     تضيفلها
    -0.73
    CW
    -0.72
    TypedValue
    -0.71
     профиль
    -0.71
     CW
    -0.71
    şte
    -0.70
     bootstrap
    -0.70
    POSITIVE LOGITS
     care
    6.31
     Care
    4.31
    care
    4.28
    Care
    3.94
     cares
    3.75
     cared
    3.70
     CARE
    3.47
    CARE
    3.28
     cuidado
    2.67
     caring
    2.48
    Act Density 0.027%

    No Known Activations