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

    Neuronpedia

    INDEX
    Explanations

    sequence of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atributos
    0.35
    ór
    0.34
    गिरी
    0.33
    ەت
    0.32
    ჩევ
    0.32
    ibilidade
    0.32
    鹖
    0.32
    createdAt
    0.31
    გი
    0.31
    ੳ
    0.31
    POSITIVE LOGITS
     calma
    0.35
     Further
    0.34
     successively
    0.34
    0.33
    ...\
    0.33
     än
    0.31
     следующих
    0.31
     proceeding
    0.30
     farther
    0.30
     further
    0.30
    Act Density 0.081%

    No Known Activations