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

    Neuronpedia

    INDEX
    Explanations

    historic buildings and conservation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Insert
    0.59
     Insert
    0.56
     INSERT
    0.56
    insert
    0.55
     insert
    0.55
     inserts
    0.54
     Wag
    0.54
    Inserting
    0.54
    Wagner
    0.53
     insertar
    0.52
    POSITIVE LOGITS
     Conservation
    0.81
     conservation
    0.80
    Conservation
    0.74
    conservation
    0.68
     conserved
    0.57
     Conserv
    0.54
     konzerv
    0.53
     conserv
    0.52
     conserve
    0.48
     supplemental
    0.47
    Act Density 0.000%

    No Known Activations