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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ville
    -0.68
    o
    -0.59
    er
    -0.50
    or
    -0.50
     
    -0.49
    e
    -0.49
    es
    -0.48
    ren
    -0.47
    oare
    -0.47
    en
    -0.46
    POSITIVE LOGITS
    expandindo
    1.09
    MemoryWarning
    0.99
    aarrggbb
    0.96
    CloseOperation
    0.94
     Roskov
    0.93
    Sucesor
    0.91
     Мексичка
    0.91
    ьаж
    0.90
    parsedMessage
    0.90
    HideFlags
    0.89
    Act Density 0.073%

    No Known Activations