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

    Neuronpedia

    INDEX
    Explanations

    infested populated

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     housed
    0.86
     welcomed
    0.86
     enshrined
    0.84
     welcome
    0.83
     confined
    0.78
     contained
    0.77
     willkommen
    0.76
     stored
    0.76
     Accepted
    0.76
     expressed
    0.75
    POSITIVE LOGITS
     infested
    1.72
     visited
    1.70
     inhabited
    1.62
     invaded
    1.60
     occupied
    1.57
     populated
    1.42
    infested
    1.41
     colonized
    1.41
     frequented
    1.40
    occupied
    1.40
    Act Density 0.514%

    No Known Activations