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

    Neuronpedia

    INDEX
    Explanations

    .I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拜
    -0.07
     Flint
    -0.07
    tiles
    -0.07
    inan
    -0.07
     MILF
    -0.06
     td
    -0.06
    Enemy
    -0.06
     parasite
    -0.06
     trie
    -0.06
    .assertIn
    -0.06
    POSITIVE LOGITS
     muster
    0.07
    เมตร
    0.06
     повинні
    0.06
     oportun
    0.06
     Wiki
    0.06
     pense
    0.06
     usually
    0.06
     increment
    0.06
     attire
    0.06
     strategist
    0.06
    Act Density 0.001%

    No Known Activations