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

    Neuronpedia

    INDEX
    Explanations

    stochastic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usuario
    -0.06
    ueblo
    -0.06
    lying
    -0.06
     국내
    -0.06
     temporada
    -0.06
    (labels
    -0.06
     dm
    -0.06
     pazar
    -0.06
     palabras
    -0.06
    drawable
    -0.06
    POSITIVE LOGITS
    ρκ
    0.08
    .Delay
    0.07
     stochastic
    0.07
    .promise
    0.06
     somew
    0.06
    Ast
    0.06
    tsx
    0.06
    ılmaktadır
    0.06
    위를
    0.06
    "W
    0.06
    Act Density 0.016%

    No Known Activations