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

    Neuronpedia

    INDEX
    Explanations

    bolognese and Bologna

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াপা
    0.38
    bridal
    0.38
    لاة
    0.37
     CCSDT
    0.35
     dazz
    0.35
    幫助
    0.35
    snake
    0.34
     Christendom
    0.34
     Elton
    0.34
    级别
    0.33
    POSITIVE LOGITS
     Bologna
    1.13
     Bolog
    1.09
     bolognese
    1.03
     bolog
    1.02
     rag
    0.82
     Rag
    0.70
     Bolo
    0.69
    Rag
    0.65
     bolo
    0.63
    rag
    0.60
    Act Density 0.003%

    No Known Activations