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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ONENT
    -0.07
    й
    -0.06
    (provider
    -0.06
    .Currency
    -0.06
    ์โ
    -0.06
    park
    -0.06
     containers
    -0.06
     rumours
    -0.06
     коллек
    -0.06
    Diagram
    -0.06
    POSITIVE LOGITS
    Route
    0.07
     کمتر
    0.07
    loser
    0.07
    (rp
    0.06
    .im
    0.06
     Homo
    0.06
    акон
    0.06
     Anch
    0.06
    /at
    0.06
    (spec
    0.06
    Act Density 0.001%

    No Known Activations