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

    Neuronpedia

    INDEX
    Explanations

    projectors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quentin
    -0.07
    eming
    -0.07
    oration
    -0.07
    .websocket
    -0.06
    MN
    -0.06
    spa
    -0.06
    جار
    -0.06
     ledger
    -0.06
     Eaton
    -0.06
    ického
    -0.06
    POSITIVE LOGITS
     Lover
    0.06
    .GetName
    0.06
    .hash
    0.06
    /rfc
    0.06
    -buy
    0.06
     sweating
    0.06
    ュ
    0.06
    (Tag
    0.06
     계
    0.06
     num
    0.06
    Act Density 0.024%

    No Known Activations