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

    Neuronpedia

    INDEX
    Explanations

    letter d followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۹
    1.20
    1.19
    ৯
    1.16
    9
    1.07
     que
    1.01
     Oversight
    1.01
     dejaron
    1.01
     tutte
    1.00
     veneers
    1.00
     allong
    1.00
    POSITIVE LOGITS
    cU
    1.19
    Ĭ
    1.16
    ם
    1.15
    yczny
    1.09
    zelfde
    1.08
    녕하십니까
    1.05
    此之外
    1.05
    ed
    1.02
    cactus
    1.02
    iéndose
    1.02
    Act Density 0.148%

    No Known Activations