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

    Neuronpedia

    INDEX
    Explanations

    IRS, legal forms, tax documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hört
    0.41
    欧盟
    0.38
     বর্ত
    0.38
    撚
    0.38
    otid
    0.38
     Kran
    0.38
     hém
    0.37
     rémun
    0.37
     nieuws
    0.37
    ార్క్
    0.37
    POSITIVE LOGITS
     Aval
    0.54
    Aval
    0.51
    irmi
    0.44
     aval
    0.43
     Avalon
    0.43
     Just
    0.41
     Northwest
    0.41
     Find
    0.40
    Just
    0.38
     Turbo
    0.38
    Act Density 0.004%

    No Known Activations