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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    justify
    -0.08
    Quit
    -0.07
    Imagine
    -0.07
     astronauts
    -0.07
     angel
    -0.07
     Fé
    -0.07
     ui
    -0.06
     �
    -0.06
     Onun
    -0.06
     self
    -0.06
    POSITIVE LOGITS
    84
    0.07
    cordova
    0.07
     Burns
    0.06
     mạng
    0.06
    .netty
    0.06
     serviços
    0.06
     molding
    0.06
    /high
    0.06
     Spy
    0.06
     školy
    0.06
    Act Density 0.024%

    No Known Activations