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

    Neuronpedia

    INDEX
    Explanations

    Web server configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ordered
    -0.08
     imprison
    -0.07
    ística
    -0.07
     Canada
    -0.07
     sí
    -0.06
    मत
    -0.06
     Bro
    -0.06
     qualified
    -0.06
    Kernel
    -0.06
     Wolverine
    -0.06
    POSITIVE LOGITS
     UIL
    0.06
     pct
    0.06
     걸
    0.06
    <Block
    0.06
     pnl
    0.05
    <Cell
    0.05
     Indonesian
    0.05
     Нат
    0.05
     opposes
    0.05
    اشته
    0.05
    Act Density 0.116%

    No Known Activations