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

    Neuronpedia

    INDEX
    Explanations

    processes of creation and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हुन्छ
    0.87
     спраши
    0.82
    izaciones
    0.81
     deje
    0.80
    znym
    0.79
    勉強
    0.79
     когда
    0.77
    㚐
    0.75
    ણો
    0.74
     মানুষ
    0.73
    POSITIVE LOGITS
     کردن
    0.99
    ירת
    0.85
     شدن
    0.85
    abling
    0.80
    และการ
    0.79
     unor
    0.77
    owanie
    0.76
    uing
    0.76
    ierung
    0.76
     ء
    0.74
    Act Density 0.247%

    No Known Activations