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

    Neuronpedia

    INDEX
    Explanations

    briefly describe or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     леген
    0.48
     herr
    0.47
     фла
    0.47
     Poste
    0.46
     NAT
    0.46
     estrella
    0.45
     फ्ले
    0.45
    兎
    0.45
     emblem
    0.44
     feste
    0.44
    POSITIVE LOGITS
    Habitat
    0.49
    Waterfall
    0.49
    allocate
    0.48
    Technology
    0.48
    Auction
    0.48
    Sleeping
    0.48
    Engineering
    0.48
    dau
    0.47
    Receive
    0.46
    Relative
    0.46
    Act Density 0.002%

    No Known Activations