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

    Neuronpedia

    INDEX
    Explanations

    don

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，要
    -0.07
    никами
    -0.07
    rays
    -0.06
    ;;;;;;;;;;;;;;;;
    -0.06
     jednodu
    -0.06
     люб
    -0.06
    yahoo
    -0.06
     tenga
    -0.06
    aka
    -0.06
     کاملا
    -0.06
    POSITIVE LOGITS
    643
    0.07
    tbody
    0.07
    dialog
    0.07
     unter
    0.07
     (::
    0.06
     dive
    0.06
     GIVEN
    0.06
    πουργ
    0.06
     DISPLAY
    0.06
    ονται
    0.06
    Act Density 0.011%

    No Known Activations