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

    Neuronpedia

    INDEX
    Explanations

    conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     გამო
    0.47
     Announced
    0.46
     przyję
    0.45
     ragazzi
    0.43
     중심으로
    0.42
    ীক
    0.42
     جوہری
    0.42
     Westwood
    0.42
     cookieParser
    0.41
    ুক্ত
    0.41
    POSITIVE LOGITS
    ου
    0.50
    age
    0.48
    maze
    0.44
     cib
    0.44
    امد
    0.42
    ad
    0.42
    作為
    0.42
    oulli
    0.42
    et
    0.41
    opp
    0.40
    Act Density 0.001%

    No Known Activations