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

    Neuronpedia

    INDEX
    Explanations

    Reference

    np_max-act · gemini-2.0-flash

    The neuron fires on MSBuild XML `<Reference Include="…">` entries—that is, on project file lines that declare assembly references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )="
    -0.06
     loops
    -0.06
    MI
    -0.06
    FAILED
    -0.06
    爷
    -0.06
    >{"
    -0.06
    .embedding
    -0.06
     Slots
    -0.06
     kwargs
    -0.06
    Роз
    -0.06
    POSITIVE LOGITS
     silence
    0.07
     RemoteException
    0.07
     RES
    0.07
    ικός
    0.07
     altura
    0.07
     Р
    0.06
     mat
    0.06
    ských
    0.06
    砲
    0.06
     refer
    0.06
    Act Density 0.000%

    No Known Activations