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

    Neuronpedia

    INDEX
    Explanations

    Scientific model fitting/predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flat
    -0.07
    roz
    -0.07
    宮
    -0.07
    ]->
    -0.06
     midd
    -0.06
     collaborators
    -0.06
    (client
    -0.06
    ではない
    -0.06
    =}
    -0.06
    hibited
    -0.06
    POSITIVE LOGITS
     %↵
    0.07
     iphone
    0.06
    WindowTitle
    0.06
    .animation
    0.06
     counsel
    0.06
    ({↵↵
    0.06
    %",↵
    0.06
     roomId
    0.06
    /the
    0.06
     generics
    0.06
    Act Density 0.048%

    No Known Activations