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

    Neuronpedia

    INDEX
    Explanations

    practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shipment
    -0.07
     jente
    -0.07
     claiming
    -0.06
    ),"
    -0.06
    sha
    -0.06
     nhuận
    -0.06
    jumbotron
    -0.06
    qe
    -0.06
     david
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    าการ
    0.08
    น
    0.08
     smě
    0.07
    루
    0.07
     좋은
    0.07
    лі
    0.06
     一般
    0.06
    ้าง
    0.06
     Â
    0.06
    .sap
    0.06
    Act Density 0.008%

    No Known Activations