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

    Neuronpedia

    INDEX
    Explanations

    system verilog traceability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ء
    1.21
    ງ
    1.05
    kunde
    1.03
    тавли
    1.02
    ᆼ
    1.02
     телефону
    1.02
     Lipid
    1.00
    ින
    1.00
    ൽ
    0.99
    ᆨ
    0.97
    POSITIVE LOGITS
    names
    0.98
    rownames
    0.97
    ]])
    0.94
     disguised
    0.94
     pointy
    0.92
    𝘳
    0.92
    )];
    0.91
    launcher
    0.90
    ulfonic
    0.90
    ബാ
    0.90
    Act Density 0.001%

    No Known Activations