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

    Neuronpedia

    INDEX
    Explanations

    formation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sug
    -0.06
     промислов
    -0.06
     WATER
    -0.06
     spoiled
    -0.06
     SG
    -0.06
    Word
    -0.06
    SO
    -0.06
    fir
    -0.06
     Patton
    -0.06
     वस
    -0.06
    POSITIVE LOGITS
     alguna
    0.07
     prem
    0.06
    achs
    0.06
    ;:
    0.06
    PRESS
    0.06
    ayette
    0.06
     την
    0.06
     rated
    0.06
     erm
    0.06
     durable
    0.06
    Act Density 0.013%

    No Known Activations