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

    Neuronpedia

    INDEX
    Explanations

    categories and types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .boolean
    -0.07
    ced
    -0.06
    (tags
    -0.06
    Ai
    -0.06
    medium
    -0.06
    syn
    -0.06
    .low
    -0.06
     productList
    -0.06
    (),
    -0.06
    -dev
    -0.06
    POSITIVE LOGITS
    ロン
    0.08
    (UnityEngine
    0.07
     झ
    0.07
     optimizer
    0.06
        ↵    ↵    ↵
    0.06
     záv
    0.06
     defending
    0.06
    ParameterValue
    0.06
     witnesses
    0.06
    _unix
    0.06
    Act Density 0.111%

    No Known Activations