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

    Neuronpedia

    INDEX
    Explanations

    lighting and functional objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.38
     tekst
    0.35
    _{
    0.33
    ;
    0.33
     ऑफ
    0.33
     cinéma
    0.33
     richt
    0.32
    s
    0.32
     metabolism
    0.32
    á
    0.32
    POSITIVE LOGITS
    મ
    0.44
    बी
    0.42
    ك
    0.41
    З
    0.40
    ก
    0.40
    ຳ
    0.39
    ovali
    0.38
    他に
    0.38
    વ
    0.38
    ყ
    0.37
    Act Density 0.326%

    No Known Activations