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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation for lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䀨
    0.50
    DISTANCE
    0.47
    ੪
    0.45
    izability
    0.45
     SOLUTIONS
    0.45
     конференции
    0.43
    ITATION
    0.43
     CEN
    0.43
    પુર
    0.42
    𝙳
    0.42
    POSITIVE LOGITS
     bo
    0.40
    ru
    0.40
    xh
    0.39
     pages
    0.38
     ต้องการ
    0.38
     x
    0.38
     Perl
    0.38
    血
    0.38
    0
    0.37
    x
    0.37
    Act Density 0.003%

    No Known Activations