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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الموس
    -0.07
    cctor
    -0.07
     хра
    -0.06
     нап
    -0.06
    ?v
    -0.06
    abox
    -0.06
    xcf
    -0.06
     Constructors
    -0.06
    .Av
    -0.06
     Squad
    -0.06
    POSITIVE LOGITS
    (Type
    0.07
     fiber
    0.06
    .LinearLayoutManager
    0.06
    Frequency
    0.06
    (MenuItem
    0.06
     FORE
    0.06
    Eye
    0.06
    Super
    0.06
    提示
    0.06
    Richard
    0.06
    Act Density 0.000%

    No Known Activations