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

    Neuronpedia

    INDEX
    Explanations

    Volkswagen Group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vortices
    0.51
     mücade
    0.49
     αγο
    0.48
     alarma
    0.48
     dosta
    0.47
     момент
    0.46
     माध्यम
    0.45
    危机
    0.45
     চেহারা
    0.45
    ревнова
    0.44
    POSITIVE LOGITS
     will
    0.54
    OF
    0.53
    ’
    0.47
    '
    0.46
    Ac
    0.46
     Tuesdays
    0.43
    ,
    0.43
    Style
    0.43
     Style
    0.43
     Ensures
    0.42
    Act Density 0.004%

    No Known Activations