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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ções
    -0.07
     confused
    -0.07
     teach
    -0.07
     fortunately
    -0.06
     shook
    -0.06
    stit
    -0.06
     blur
    -0.06
    .FlatStyle
    -0.06
    otic
    -0.06
    amacare
    -0.06
    POSITIVE LOGITS
    imler
    0.07
    {\"
    0.07
    ({↵
    0.07
     hãy
    0.06
     Hudson
    0.06
    ´:
    0.06
    輪
    0.06
    \.
    0.06
    WITH
    0.06
     }
↵
↵
    0.06
    Act Density 0.011%

    No Known Activations