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

    Neuronpedia

    INDEX
    Explanations

    cluster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ்க
    3.25
    ள்ளார்
    2.91
     tide
    2.66
    च्या
    2.58
     lucru
    2.56
     disebutkan
    2.50
    ✗
    2.50
    менно
    2.48
    т
    2.46
    िक
    2.44
    POSITIVE LOGITS
    ل
    4.08
    er
    4.04
    ar
    3.94
    el
    3.80
    на
    3.40
    م
    3.35
    al
    3.34
    erà
    3.17
    ാ
    3.06
    arif
    2.99
    Act Density 0.126%

    No Known Activations