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

    Neuronpedia

    INDEX
    Explanations

    before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pre
    0.96
    预
    0.84
    Pre
    0.82
     Pre
    0.80
    提前
    0.76
     प्री
    0.76
     미리
    0.75
    pre
    0.73
     pretrial
    0.73
     preorder
    0.72
    POSITIVE LOGITS
     before
    1.84
     antes
    1.66
    before
    1.54
     sebelum
    1.54
     قبل
    1.45
     før
    1.43
     voordat
    1.43
     bevor
    1.38
    Before
    1.38
     ennen
    1.36
    Act Density 0.020%

    No Known Activations