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

    Neuronpedia

    INDEX
    Explanations

    building or place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عاشق
    0.78
     progressing
    0.75
     occupying
    0.74
     embedding
    0.73
     inhabiting
    0.72
     describing
    0.70
     pursuing
    0.70
     roaming
    0.69
     formatting
    0.69
     inheriting
    0.68
    POSITIVE LOGITS
     house
    1.47
     houses
    1.40
     hosts
    1.34
     overlooks
    1.22
     accueille
    1.17
     host
    1.16
     attracts
    1.12
     accommodates
    1.12
     Houses
    1.11
     House
    1.09
    Act Density 0.127%

    No Known Activations