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

    Neuronpedia

    INDEX
    Explanations

    all or each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soorten
    1.02
     kinds
    0.81
    其他
    0.80
    המ
    0.79
    الم
    0.77
     comunes
    0.77
    מ
    0.75
     types
    0.72
    ച
    0.70
     autres
    0.69
    POSITIVE LOGITS
    𝗮
    0.84
    ется
    0.83
     has
    0.80
     is
    0.80
     này
    0.79
     کسی
    0.79
    지를
    0.75
     বিষয়টি
    0.74
     Goes
    0.72
     conforms
    0.72
    Act Density 0.110%

    No Known Activations