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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     최초
    -0.09
     hipótese
    -0.08
     favoritos
    -0.08
    aros
    -0.08
     первонач
    -0.08
    หัส
    -0.08
     etapas
    -0.08
     fave
    -0.08
     Certains
    -0.08
     기간
    -0.08
    POSITIVE LOGITS
     habitants
    0.09
    竟
    0.09
    让我
    0.08
     inhabitants
    0.08
     locals
    0.08
    営
    0.08
     देखकर
    0.07
     مردم
    0.07
     visitor
    0.07
    这里
    0.07
    Act Density 0.203%

    No Known Activations