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

    Neuronpedia

    INDEX
    Explanations

    references to various types of rails in a context related to construction or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rail and following terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ofType
    -0.51
     Sma
    -0.51
     CCC
    -0.51
    WEDNESDAY
    -0.51
     MZ
    -0.50
     Josephine
    -0.48
     Bix
    -0.47
     Ome
    -0.47
    ﹏
    -0.46
     DCT
    -0.46
    POSITIVE LOGITS
     RAIL
    1.19
     Rail
    1.09
     rail
    1.09
    Rail
    1.09
    rail
    1.02
    RAIL
    0.94
     rails
    0.90
    Rails
    0.85
    rails
    0.84
     aéreo
    0.84
    Act Density 0.008%

    No Known Activations