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

    Neuronpedia

    INDEX
    Explanations

    genes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refined
    -0.07
     bustling
    -0.07
    .Strings
    -0.07
     blazing
    -0.07
    putation
    -0.07
    RESSED
    -0.06
     zombies
    -0.06
     Macros
    -0.06
     myList
    -0.06
    ρί
    -0.06
    POSITIVE LOGITS
     Ethereum
    0.06
    _pct
    0.06
    POCH
    0.06
    agnitude
    0.06
    имости
    0.06
     Essen
    0.06
    _TOOLTIP
    0.06
    _trials
    0.06
     repar
    0.06
    (actions
    0.06
    Act Density 0.031%

    No Known Activations