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

    Neuronpedia

    INDEX
    Explanations

    determiners followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahankan
    0.84
    ナソニック
    0.84
     нажа
    0.82
    ين
    0.81
    ac
    0.79
     площа
    0.77
    ،
    0.77
    ség
    0.75
    eem
    0.75
     чыныгы
    0.75
    POSITIVE LOGITS
    .
    0.95
    ע
    0.87
     from
    0.82
     digestive
    0.81
    די
    0.79
    לי
    0.77
     that
    0.76
     appre
    0.75
    ST
    0.75
     indigestion
    0.74
    Act Density 0.000%

    No Known Activations