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

    Neuronpedia

    INDEX
    Explanations

    ampersand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [z
    -0.07
         
    -0.07
    [selected
    -0.07
    -0.06
    Moder
    -0.06
     polit
    -0.06
     Cad
    -0.06
    .Repository
    -0.06
     OMIT
    -0.06
    SectionsIn
    -0.06
    POSITIVE LOGITS
     gfx
    0.07
    برای
    0.07
    ніх
    0.07
     안
    0.06
     OR
    0.06
     Megan
    0.06
    otron
    0.06
    )?↵
    0.06
     fluor
    0.06
    ianne
    0.06
    Act Density 0.004%

    No Known Activations