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

    Neuronpedia

    INDEX
    Explanations

    checking bingo rows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    degree
    0.49
     degree
    0.49
     Degree
    0.48
    Degree
    0.48
     skyl
    0.41
    degrees
    0.39
     aspart
    0.39
    ênh
    0.39
     DEG
    0.38
     iOS
    0.38
    POSITIVE LOGITS
     bingo
    2.03
     Bingo
    1.98
    Bingo
    1.88
     bing
    1.37
    bing
    1.35
     Bing
    1.20
    Bing
    1.14
     binge
    0.91
     빙
    0.85
    INGO
    0.79
    Act Density 0.010%

    No Known Activations