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

    Neuronpedia

    INDEX
    Explanations

    vaccine and vaccination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꭸ
    0.61
    ITIONAL
    0.60
    េ
    0.60
     proclaiming
    0.60
    haired
    0.60
    \%.
    0.59
     Entretanto
    0.58
     квартиры
    0.58
    园区
    0.57
    \,\
    0.56
    POSITIVE LOGITS
    o
    0.76
    ه
    0.61
     când
    0.49
    𝒏
    0.48
     trivalent
    0.46
    ed
    0.46
     vaccine
    0.46
    ק
    0.46
     anaphyl
    0.45
    우
    0.45
    Act Density 0.040%

    No Known Activations