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

    Neuronpedia

    INDEX
    Explanations

    catch up soon though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molecular
    0.49
     endothelial
    0.48
    ה
    0.48
     legislative
    0.46
     sellers
    0.46
     tellus
    0.45
     baker
    0.44
     proclam
    0.44
     lion
    0.44
     baseApiPath
    0.44
    POSITIVE LOGITS
    OD
    0.53
    that
    0.52
    Xd
    0.51
    ный
    0.47
    obie
    0.46
    żenie
    0.46
    ider
    0.45
    чний
    0.45
    riya
    0.45
     تبدیلی
    0.44
    Act Density 0.001%

    No Known Activations