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

    Neuronpedia

    INDEX
    Explanations

    methods and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آغاز
    0.38
    شانی
    0.35
     UNNEEDED
    0.35
    ्रपान
    0.35
     notizia
    0.35
     hostilities
    0.35
    溲
    0.35
     cityName
    0.35
    给人
    0.35
     noticia
    0.34
    POSITIVE LOGITS
     methods
    0.64
     techniques
    0.63
     Bayesian
    0.58
    的方法
    0.52
     방법을
    0.52
     P
    0.50
     method
    0.50
     방법
    0.50
     methodology
    0.49
     método
    0.49
    Act Density 0.294%

    No Known Activations