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

    Neuronpedia

    INDEX
    Explanations

    Common words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mužů
    -0.07
    uben
    -0.07
    -described
    -0.06
    ursors
    -0.06
     Jama
    -0.06
    RAP
    -0.06
     scattering
    -0.06
    andid
    -0.06
     доп
    -0.06
     AppState
    -0.06
    POSITIVE LOGITS
    didn
    0.07
    !
↵
    0.07
    .convert
    0.07
    0.06
    ,W
    0.06
    porter
    0.06
    แชม
    0.06
     kích
    0.06
     enticing
    0.06
    [w
    0.06
    Act Density 0.000%

    No Known Activations