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

    Neuronpedia

    INDEX
    Explanations

    li

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overt
    -0.07
    .compose
    -0.07
    Ub
    -0.07
    Storyboard
    -0.06
     název
    -0.06
     understandable
    -0.06
     Uber
    -0.06
    デル
    -0.06
     uv
    -0.06
     sắp
    -0.06
    POSITIVE LOGITS
     pelvic
    0.08
     Lives
    0.07
    UTERS
    0.07
    Democratic
    0.07
    nie
    0.07
    MI
    0.07
    ayi
    0.07
     Liam
    0.06
    IRECT
    0.06
     Loves
    0.06
    Act Density 0.009%

    No Known Activations