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

    Neuronpedia

    INDEX
    Explanations

    initiating plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ছবি
    0.42
     didn
    0.38
    主な
    0.35
     doodle
    0.35
    几何
    0.35
     trò
    0.34
    小程序
    0.34
     helpers
    0.34
     różne
    0.34
     খালি
    0.34
    POSITIVE LOGITS
    打造
    0.43
     ormai
    0.42
     상당히
    0.42
     langfrist
    0.41
     ambitious
    0.41
     নিঃসন্দেহে
    0.40
     Sélection
    0.38
     अत्यंत
    0.38
    Assuming
    0.37
     mijn
    0.37
    Act Density 0.100%

    No Known Activations