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

    Neuronpedia

    INDEX
    Explanations

    replace or next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    archiwizowane
    0.46
     ני
    0.46
     mans
    0.44
    anfaatkan
    0.44
    acchati
    0.43
    assade
    0.43
    api
    0.42
     rese
    0.42
    anceled
    0.42
     راز
    0.42
    POSITIVE LOGITS
    Yellow
    0.55
     König
    0.51
    Игра
    0.49
     Yellow
    0.48
     kombin
    0.48
     येलो
    0.47
     Combin
    0.45
     Oahu
    0.45
     Vorteil
    0.45
     Tap
    0.44
    Act Density 0.004%

    No Known Activations