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

    Neuronpedia

    INDEX
    Explanations

    web links or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Suit
    0.42
    leys
    0.41
     nr
    0.37
     Suit
    0.37
     Pisc
    0.37
    Pasta
    0.36
     Deleg
    0.36
     القط
    0.36
     السابق
    0.36
     빈
    0.36
    POSITIVE LOGITS
    原子力
    0.40
     vă
    0.40
    Segmentation
    0.39
     wallets
    0.38
     अबाउट
    0.38
    $.}
    0.38
    Appellant
    0.36
     bottoms
    0.36
    ாம்
    0.36
    ).}
    0.36
    Act Density 0.003%

    No Known Activations