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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potrav
    -0.07
    _quota
    -0.07
     Shut
    -0.07
    .httpClient
    -0.06
    nt
    -0.06
    達
    -0.06
     adb
    -0.06
    yard
    -0.06
    stu
    -0.06
    áb
    -0.06
    POSITIVE LOGITS
     hiện
    0.07
    isi
    0.07
    Team
    0.06
     socioeconomic
    0.06
    本当に
    0.06
     RemoteException
    0.06
    Added
    0.06
    Nie
    0.06
    ==='
    0.06
     piston
    0.06
    Act Density 0.006%

    No Known Activations