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

    Neuronpedia

    INDEX
    Explanations

    to help ask for more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoid
    1.16
     choose
    1.00
    避免
    0.92
    avoid
    0.90
    Avoid
    0.90
     jot
    0.89
     evitar
    0.86
     Avoid
    0.85
     stay
    0.84
     говоря
    0.83
    POSITIVE LOGITS
    ніка
    0.89
    자들이
    0.86
    เคราะห์
    0.85
     pptd
    0.82
     manpower
    0.82
    लिट
    0.80
     Helps
    0.80
     موجود
    0.79
     جزء
    0.79
     helps
    0.79
    Act Density 0.011%

    No Known Activations