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

    Neuronpedia

    INDEX
    Explanations

    before or since a context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.97
    a
    0.92
    u
    0.89
    et
    0.87
    el
    0.81
    া
    0.78
    za
    0.71
    er
    0.70
    ri
    0.68
    ूहिक
    0.68
    POSITIVE LOGITS
     Embora
    0.90
    ;\;\
    0.82
    الم
    0.80
    󰡔
    0.78
    МА
    0.78
     cognizant
    0.77
    搠
    0.76
    𝘦
    0.76
    īga
    0.76
     hänen
    0.76
    Act Density 0.199%

    No Known Activations