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

    Neuronpedia

    INDEX
    Explanations

    given names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Error
    0.48
    procedure
    0.46
    Для
    0.46
    Mrs
    0.46
    http
    0.45
    0.44
    И
    0.43
    object
    0.43
    Про
    0.42
    sns
    0.42
    POSITIVE LOGITS
     Jones
    0.68
     Miller
    0.67
     Zelensky
    0.66
     Johnson
    0.66
     Clarke
    0.64
     Franklin
    0.64
     Smith
    0.64
     הש
    0.63
     Skywalker
    0.63
     Biden
    0.63
    Act Density 0.071%

    No Known Activations