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

    Neuronpedia

    INDEX
    Explanations

    Bel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     berlin
    -0.07
    ，都
    -0.06
     Wort
    -0.06
     CHECK
    -0.06
     Orchard
    -0.06
     STR
    -0.06
    NewUrlParser
    -0.06
     Maison
    -0.06
    ไฟ
    -0.06
    (dto
    -0.06
    POSITIVE LOGITS
     Milli
    0.07
     menacing
    0.07
     pioneered
    0.07
    angling
    0.07
    IFI
    0.06
    ॉक
    0.06
    entar
    0.06
    ;++
    0.06
    \application
    0.06
     مك
    0.06
    Act Density 0.001%

    No Known Activations