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

    Neuronpedia

    INDEX
    Explanations

    observing thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曇
    0.93
     настолько
    0.89
     confirmado
    0.88
    Versions
    0.88
     befindet
    0.87
    اریخ
    0.83
    compare
    0.82
     accus
    0.81
     confirming
    0.81
     numbered
    0.80
    POSITIVE LOGITS
     advice
    1.71
     recommendations
    1.56
     consejos
    1.53
     توصیه
    1.52
     방법을
    1.47
     TIPS
    1.47
     precepts
    1.46
    実践
    1.44
     방법
    1.43
     方法
    1.42
    Act Density 0.539%

    No Known Activations