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

    Neuronpedia

    INDEX
    Explanations

    children being born

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     already
    -1.64
    已经
    -1.62
     currently
    -1.41
     or
    -1.29
    目前
    -1.19
     уже
    -1.17
    已
    -1.15
     recently
    -1.13
     will
    -1.12
     on
    -1.09
    POSITIVE LOGITS
     later
    1.30
     álcool
    1.11
     nă
    1.10
    都知道
    1.06
     позже
    1.06
     выборе
    1.05
     hongos
    1.01
    鲠
    1.01
     posteriormente
    1.00
     kés
    1.00
    Act Density 0.004%

    No Known Activations