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

    Neuronpedia

    INDEX
    Explanations

    if ... then .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nếu
    0.51
     kalau
    0.50
     hvis
    0.49
     eğer
    0.49
     اگر
    0.49
     जेव्हा
    0.48
    要是
    0.48
     যদি
    0.47
     اگه
    0.47
     jika
    0.47
    POSITIVE LOGITS
     then
    2.52
     allora
    2.33
    then
    2.27
     entonces
    2.17
     então
    2.09
    则
    2.03
     thì
    2.00
     тогда
    1.98
     alors
    1.97
     τότε
    1.96
    Act Density 0.191%

    No Known Activations