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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungal
    -0.07
    Js
    -0.07
     parties
    -0.06
    encoded
    -0.06
    oth
    -0.06
    -feature
    -0.06
     indian
    -0.06
    ад
    -0.06
    ายใน
    -0.06
     panor
    -0.06
    POSITIVE LOGITS
    .Router
    0.06
    .AutoScaleDimensions
    0.06
     dnes
    0.05
     Clar
    0.05
    Books
    0.05
     Ivanka
    0.05
     지금
    0.05
    "testing
    0.05
     ма
    0.05
    what
    0.05
    Act Density 0.028%

    No Known Activations