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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spéc
    0.69
     keyword
    0.63
    俑
    0.59
     especific
    0.59
     spec
    0.58
    해가
    0.58
     ريد
    0.58
    сько
    0.57
    ¡
    0.57
     পুরা
    0.57
    POSITIVE LOGITS
     Moses
    1.37
     Joseph
    1.31
     Samuel
    1.29
     Godfrey
    1.26
    Moses
    1.25
     Wilfred
    1.24
    Joseph
    1.23
     Emmanuel
    1.19
     Stephen
    1.18
     Charles
    1.18
    Act Density 0.008%

    No Known Activations