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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hovering
    -0.07
    왔
    -0.07
    Không
    -0.06
    hidden
    -0.06
     Democrats
    -0.06
     palace
    -0.06
     rs
    -0.06
     █
    -0.06
    “One
    -0.06
     nonprofits
    -0.06
    POSITIVE LOGITS
     addAction
    0.07
    dash
    0.07
    Bezier
    0.07
    ोकर
    0.07
    lico
    0.07
    lazy
    0.06
    lement
    0.06
    ).\
    0.06
    .asset
    0.06
     ж
    0.06
    Act Density 0.011%

    No Known Activations