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

    Neuronpedia

    INDEX
    Explanations

    time indicator am/pm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    -1.12
     الوطنية
    -0.98
     pels
    -0.93
     to
    -0.92
     seemingly
    -0.91
     some
    -0.90
    reuters
    -0.89
     their
    -0.87
     septembre
    -0.81
     quite
    -0.80
    POSITIVE LOGITS
    pm
    1.20
     pm
    1.08
     ощущение
    1.02
     rembour
    1.01
     любы
    1.00
    viene
    0.99
     EIGHT
    0.96
     coté
    0.96
    を見ると
    0.94
    ötä
    0.93
    Act Density 0.003%

    No Known Activations