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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BindingUtil
    -0.07
     GtkWidget
    -0.07
    _gb
    -0.07
    reeting
    -0.06
    кі
    -0.06
    Titles
    -0.06
     Thames
    -0.06
    .responses
    -0.06
    ственные
    -0.06
    _documento
    -0.06
    POSITIVE LOGITS
     L
    0.07
    L
    0.07
    ً،
    0.06
     Coke
    0.06
     NV
    0.06
     Warehouse
    0.06
     EL
    0.06
     κι
    0.06
    ЕТ
    0.06
     BM
    0.06
    Act Density 0.044%

    No Known Activations