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

    Neuronpedia

    INDEX
    Explanations

    restaurants and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bun
    0.41
    las
    0.39
    প্রণ
    0.39
     Bun
    0.38
     vanishing
    0.38
     VB
    0.38
     alami
    0.38
     Smiley
    0.37
     garland
    0.37
     伊
    0.36
    POSITIVE LOGITS
     Delta
    0.57
     delta
    0.57
    Delta
    0.56
    delta
    0.55
     Fairmont
    0.48
    DELTA
    0.48
     Sutton
    0.44
    ಸ್ಯ
    0.42
     Keg
    0.42
     keg
    0.42
    Act Density 0.003%

    No Known Activations