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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coat
    -0.08
     bookmarks
    -0.07
     상
    -0.07
     Glam
    -0.07
    МО
    -0.07
     Reyes
    -0.06
     تاث
    -0.06
    NOP
    -0.06
    <TSource
    -0.06
     Ham
    -0.06
    POSITIVE LOGITS
    stacle
    0.06
    .isEnabled
    0.06
    .Now
    0.06
     incremental
    0.06
     расстоя
    0.06
     =>$
    0.06
     Wine
    0.06
    sPid
    0.06
     Leads
    0.05
    ')){↵
    0.05
    Act Density 0.001%

    No Known Activations