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

    Neuronpedia

    INDEX
    Explanations

    wood, stone, tiling, flooring, walls, cladding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     humoral
    0.45
     arousal
    0.44
     stopwords
    0.42
     nltk
    0.41
     doctr
    0.40
     consensual
    0.39
     statist
    0.39
     Yoon
    0.37
     currentUser
    0.37
     unreasonable
    0.37
    POSITIVE LOGITS
     flooring
    1.21
     walls
    1.00
     Flooring
    0.97
     wood
    0.96
     floors
    0.94
     cladding
    0.89
     tiles
    0.86
     panels
    0.86
     tiled
    0.85
     tiling
    0.85
    Act Density 0.026%

    No Known Activations