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

    Neuronpedia

    INDEX
    Explanations

    bye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provisioning
    -0.07
    وقع
    -0.07
     方法
    -0.07
     jihad
    -0.07
    ollywood
    -0.07
    WWW
    -0.07
     sound
    -0.07
    ounding
    -0.07
     압
    -0.07
     тов
    -0.06
    POSITIVE LOGITS
     Bye
    0.10
     bye
    0.09
    oredProcedure
    0.06
    .alignment
    0.06
     educating
    0.06
     eyel
    0.05
     pee
    0.05
    signIn
    0.05
     herpes
    0.05
    /bus
    0.05
    Act Density 0.001%

    No Known Activations