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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain specific text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     game
    0.38
     Holi
    0.36
    game
    0.36
    乃至
    0.36
    مون
    0.35
     Paston
    0.35
     Dragon
    0.33
     Blue
    0.33
    okon
    0.33
     Hound
    0.33
    POSITIVE LOGITS
     ର
    0.43
     -!
    0.41
     '}';
    0.41
     へ
    0.40
     !***
    0.39
    ញ្
    0.38
     jTextField
    0.38
     pestaña
    0.38
     କ
    0.38
    ícul
    0.37
    Act Density 0.235%

    No Known Activations