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

    Neuronpedia

    INDEX
    Explanations

    latitude longitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     constructed
    -0.06
    Women
    -0.06
    ethe
    -0.06
     envelope
    -0.06
    Yet
    -0.06
    FD
    -0.06
     Informationen
    -0.06
     accommodations
    -0.06
     provisions
    -0.06
    progress
    -0.06
    POSITIVE LOGITS
    ，更
    0.07
     deserving
    0.06
     Steve
    0.06
    ุก
    0.06
    immers
    0.06
    (The
    0.06
     emple
    0.06
    лас
    0.06
     %@",
    0.06
    setState
    0.06
    Act Density 0.008%

    No Known Activations