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

    Neuronpedia

    INDEX
    Explanations

    DIY crafts and collecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GeV
    0.46
     probing
    0.43
     nonatomic
    0.42
     superficies
    0.40
     confidentiality
    0.38
     counterv
    0.38
     overlying
    0.38
     unsubstituted
    0.38
     confounding
    0.37
     Timatic
    0.37
    POSITIVE LOGITS
     handmade
    1.33
    handmade
    1.13
     Handmade
    1.09
     homemade
    1.09
     handcrafted
    1.07
     succulents
    1.03
     crafts
    0.99
     pottery
    0.98
    DIY
    0.98
     candles
    0.98
    Act Density 0.054%

    No Known Activations