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

    Neuronpedia

    INDEX
    Explanations

    Silicon Valley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imasmim
    1.03
     vattati
    1.02
     vasena
    1.02
     supremely
    0.98
    اسية
    0.98
     μεγάλη
    0.96
     natthi
    0.94
    犇
    0.93
    ﺩ
    0.92
     جوړونک
    0.90
    POSITIVE LOGITS
    ’
    2.05
    ↵
    1.56
    '
    1.55
    -
    1.38
     Silicon
    1.31
    an
    1.24
    ↵↵
    1.23
    1.21
    are
    1.16
    he
    1.16
    Act Density 0.002%

    No Known Activations