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

    Neuronpedia

    INDEX
    Explanations

    index variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pride
    -0.07
     Gina
    -0.07
    .Permission
    -0.06
     adlandır
    -0.06
     Regents
    -0.06
     Commonwealth
    -0.06
     année
    -0.06
     substring
    -0.06
     Passion
    -0.06
    ену
    -0.06
    POSITIVE LOGITS
    ,[
    0.06
     )
↵
    0.06
    습
    0.06
     SUCCESS
    0.06
    %",↵
    0.06
     wrinkles
    0.06
     WX
    0.06
    (DIR
    0.06
     adapt
    0.06
     ')';↵
    0.06
    Act Density 0.006%

    No Known Activations