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

    Neuronpedia

    INDEX
    Explanations

    United

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahy
    -0.07
     microbes
    -0.06
     input
    -0.06
     Linda
    -0.06
     Linh
    -0.06
    	In
    -0.06
    الي
    -0.06
    ामन
    -0.06
     pages
    -0.06
    ki
    -0.06
    POSITIVE LOGITS
     dedim
    0.07
    Produces
    0.06
     efficacy
    0.06
    /bash
    0.06
     başlar
    0.06
    .yang
    0.06
    .streaming
    0.06
    .SH
    0.06
     bathing
    0.06
    dotenv
    0.06
    Act Density 0.017%

    No Known Activations