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

    Neuronpedia

    INDEX
    Explanations

    Code/Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    事
    -0.07
     rhythms
    -0.07
     บาง
    -0.07
    edio
    -0.06
    ALTH
    -0.06
    (back
    -0.06
    、三
    -0.06
    (Max
    -0.06
     CLASS
    -0.06
     deceased
    -0.06
    POSITIVE LOGITS
    _export
    0.07
    vk
    0.06
     einmal
    0.06
    ristol
    0.06
    -re
    0.06
     Initially
    0.06
     luaL
    0.06
    Apollo
    0.06
     중요
    0.06
    /themes
    0.06
    Act Density 0.001%

    No Known Activations