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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pragma
    -0.08
    <<<<<<<
    -0.07
     Baxter
    -0.07
    ____
    -0.07
    axter
    -0.07
    >*</
    -0.06
    actors
    -0.06
    -0.06
     ########
    -0.06
    *******
    -0.06
    POSITIVE LOGITS
    040
    0.07
    .vertex
    0.07
     막
    0.06
     Legion
    0.06
     WAIT
    0.06
     Chevy
    0.06
     Vad
    0.06
    /il
    0.06
     June
    0.05
     Skip
    0.05
    Act Density 0.002%

    No Known Activations