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

    Neuronpedia

    INDEX
    Explanations

    Chosen one stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertet
    -0.08
    huizen
    -0.08
     nice
    -0.07
     agréable
    -0.07
     eventuele
    -0.07
    uň
    -0.07
     sediment
    -0.07
     קצת
    -0.07
     কঠ
    -0.07
     бытов
    -0.07
    POSITIVE LOGITS
     prophecy
    0.11
     destiny
    0.11
     heirs
    0.09
     bestowed
    0.09
    救世
    0.09
    hecy
    0.09
     decrypt
    0.08
     someday
    0.08
     destined
    0.08
     Needed
    0.08
    Act Density 0.024%

    No Known Activations