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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尖
    -0.07
     sức
    -0.07
     رمضان
    -0.06
    níku
    -0.06
    ãeste
    -0.06
     olsa
    -0.06
    しています
    -0.06
     olanlar
    -0.06
    солют
    -0.06
     Cumhurbaş
    -0.06
    POSITIVE LOGITS
    gro
    0.06
     nghị
    0.06
    rious
    0.06
     voy
    0.06
    yp
    0.06
    men
    0.06
    .ta
    0.06
    _DROP
    0.06
     ecl
    0.06
     الذين
    0.06
    Act Density 0.006%

    No Known Activations