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

    Neuronpedia

    INDEX
    Explanations

    and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zynarod
    0.71
     тобто
    0.70
     щоб
    0.66
     תו
    0.64
    BIUM
    0.64
    HAPPY
    0.64
    Makanan
    0.64
    RADIATION
    0.63
    Vacc
    0.63
     電
    0.62
    POSITIVE LOGITS
     and
    1.53
     ਅਤੇ
    1.18
     आणि
    1.16
     மற்றும்
    1.12
    และ
    1.09
     અને
    1.08
     এবং
    1.07
     और
    1.06
     or
    0.98
     и
    0.98
    Act Density 0.001%

    No Known Activations