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

    Neuronpedia

    INDEX
    Explanations

    foreign words and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.52
    1
    0.50
    2
    0.49
    .
    0.47
    )
    0.47
     =
    0.45
    That
    0.44
    5
    0.44
     That
    0.43
    9
    0.43
    POSITIVE LOGITS
     résist
    0.49
    avacak
    0.45
     svært
    0.45
     plupart
    0.44
     odpor
    0.43
     aerospace
    0.42
     አንዳንድ
    0.41
    кансер
    0.41
     avión
    0.41
     ખૂબ
    0.40
    Act Density 0.046%

    No Known Activations