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

    Neuronpedia

    INDEX
    Explanations

    code and iterative methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhaustive
    -0.08
    Cache
    -0.07
     occupation
    -0.07
     ಕೈ
    -0.07
     volvió
    -0.07
     dilig
    -0.07
     occupational
    -0.07
     order
    -0.07
     ഓഫീസ
    -0.07
     daily
    -0.07
    POSITIVE LOGITS
    iyors
    0.09
    ーカー
    0.09
     Incl
    0.09
     Sinclair
    0.08
    旅行
    0.08
    াদ
    0.08
    >Your
    0.08
    န္း
    0.08
     إقامة
    0.08
     gefallen
    0.08
    Act Density 0.001%

    No Known Activations