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

    Neuronpedia

    INDEX
    Explanations

    wood finishes and oils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    郫
    0.45
    𒈠
    0.43
    莴
    0.41
    మా
    0.41
    箜
    0.41
     ইতিহাস
    0.40
    㑒
    0.40
    Má
    0.40
    몽
    0.39
    кову
    0.39
    POSITIVE LOGITS
     waterproofing
    0.49
     aceite
    0.43
     penetration
    0.41
     bois
    0.39
     wood
    0.39
     impregnation
    0.38
     decking
    0.38
     Penet
    0.37
     deck
    0.37
     tung
    0.37
    Act Density 0.002%

    No Known Activations