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

    Neuronpedia

    INDEX
    Explanations

    opening parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ͡
    1.01
     Букмекерлер
    0.98
    ይም
    0.93
    竝
    0.91
     Букмекердик
    0.88
    ".*:
    0.86
    \%).
    0.84
    ٸ
    0.83
    乆
    0.83
    })$;
    0.83
    POSITIVE LOGITS
     (
    6.84
    （
    5.14
     （
    4.93
    (
    4.52
     ((
    4.09
     ([
    4.03
     ($
    4.02
     (“
    3.98
     ('
    3.97
     ("
    3.97
    Act Density 4.483%

    No Known Activations