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

    Neuronpedia

    INDEX
    Explanations

    elaboration on comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.84
    ing
    0.78
     if
    0.73
     the
    0.69
    ed
    0.66
     to
    0.65
    if
    0.64
    ot
    0.64
      
    0.63
     people
    0.63
    POSITIVE LOGITS
     kapsamında
    0.75
     vínculos
    0.74
    Eine
    0.73
    صیٰ
    0.68
     denominado
    0.67
    Соцмережа
    0.66
    🈺
    0.66
    💟
    0.65
     içeren
    0.65
    ا۔
    0.65
    Act Density 3.122%

    No Known Activations