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

    Neuronpedia

    INDEX
    Explanations

    given or following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprac
    0.39
    瀣
    0.38
     nowych
    0.36
     poucos
    0.34
     infrastrukt
    0.34
     nuevas
    0.34
     पटा
    0.33
     durchaus
    0.33
    માન્ય
    0.33
    วัส
    0.33
    POSITIVE LOGITS
     siguiente
    0.54
     given
    0.52
     Given
    0.51
     this
    0.45
     five
    0.45
     seguente
    0.45
     इस
    0.42
    given
    0.42
     निम्नलिखित
    0.41
     seguenti
    0.41
    Act Density 0.199%

    No Known Activations