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

    Neuronpedia

    INDEX
    Explanations

    isn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =df
    -0.07
     teor
    -0.07
     yup
    -0.06
     //#
    -0.06
    cern
    -0.06
    "strings
    -0.06
     analys
    -0.06
     الرو
    -0.06
    _mot
    -0.06
    สำเร
    -0.06
    POSITIVE LOGITS
     gunfire
    0.06
     necesario
    0.06
    licos
    0.06
     Characters
    0.06
    _Options
    0.06
    避
    0.06
    orghini
    0.06
    avin
    0.06
     tetas
    0.06
     Connections
    0.06
    Act Density 0.003%

    No Known Activations