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

    Neuronpedia

    INDEX
    Explanations

    noun followed by opening parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Букмекерлер
    0.85
     ͡
    0.77
    <unused209>
    0.77
    
    0.75
     بالټ
    0.75
    ራሉ
    0.74
     букмекерлер
    0.73
    ٸ
    0.73
    ગે
    0.73
    ходит
    0.72
    POSITIVE LOGITS
     (
    6.48
    （
    5.14
     （
    4.72
    (
    4.47
     ([
    4.15
     ($
    4.07
     ("
    4.04
     ('
    4.01
     (“
    3.92
     ((
    3.91
    Act Density 4.081%

    No Known Activations