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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [m
    -0.07
    imo
    -0.07
     ilişk
    -0.06
    _counter
    -0.06
    �택
    -0.06
     beds
    -0.06
    ((_
    -0.06
    lude
    -0.06
    uru
    -0.06
     душ
    -0.06
    POSITIVE LOGITS
    main
    0.07
    .GridColumn
    0.07
     linspace
    0.07
     замен
    0.06
    TextBoxColumn
    0.06
     repetitions
    0.06
     Sanity
    0.06
    dro
    0.06
    لیسی
    0.06
     повин
    0.06
    Act Density 0.022%

    No Known Activations