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

    Neuronpedia

    INDEX
    Explanations

    Select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    refix
    -0.08
    includes
    -0.07
    amber
    -0.06
    /api
    -0.06
     manera
    -0.06
    ха
    -0.06
    ichni
    -0.06
     buna
    -0.06
     JSON
    -0.06
     billig
    -0.06
    POSITIVE LOGITS
     Bankası
    0.07
    áce
    0.06
     FUNCTIONS
    0.06
     fashionable
    0.06
     affiliated
    0.06
     Wanted
    0.06
    ColumnsMode
    0.06
     Carolina
    0.06
     Indianapolis
    0.06
     tempered
    0.06
    Act Density 0.004%

    No Known Activations