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

    Neuronpedia

    INDEX
    Explanations

    accommodation features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sumptuous
    0.42
    Venue
    0.42
     Royale
    0.40
     impressive
    0.39
    Labour
    0.38
     Etihad
    0.38
     Labour
    0.37
     amput
    0.37
     فاس
    0.37
     Agora
    0.36
    POSITIVE LOGITS
     pets
    0.62
    pets
    0.56
     WLAN
    0.55
     chiens
    0.54
     반려동
    0.53
     towels
    0.52
    Pets
    0.52
     Tourist
    0.52
     animali
    0.50
     tourist
    0.49
    Act Density 0.001%

    No Known Activations