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

    Neuronpedia

    INDEX
    Explanations

    tatar, Tats, tatsu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Venice
    0.40
     الاجتماعي
    0.40
     backs
    0.38
     IPA
    0.38
     Ju
    0.37
    overlap
    0.37
     Moore
    0.36
     Oriental
    0.36
     নিক্ষে
    0.35
    ᱽ
    0.35
    POSITIVE LOGITS
    Label
    0.43
    LABEL
    0.41
    Triplet
    0.38
    Untitled
    0.37
    Steven
    0.37
    CART
    0.36
    Ric
    0.36
    Tac
    0.36
     Subsec
    0.36
    Cic
    0.36
    Act Density 0.001%

    No Known Activations