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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fingers
    -0.07
     denen
    -0.06
     notifyDataSetChanged
    -0.06
    못
    -0.06
     ACA
    -0.06
    يكي
    -0.06
    .Upload
    -0.06
    _END
    -0.06
     territories
    -0.06
     renovated
    -0.06
    POSITIVE LOGITS
     신규
    0.07
    orage
    0.07
    sequently
    0.06
    curr
    0.06
    (cid
    0.06
    Carthy
    0.06
     nrows
    0.06
    difficulty
    0.06
     Really
    0.06
     život
    0.06
    Act Density 0.162%

    No Known Activations