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

    Neuronpedia

    INDEX
    Explanations

    legal term of art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouvoir
    0.46
    জীবন
    0.40
     சமூக
    0.40
     সামাজিক
    0.40
    lighet
    0.40
     ताकत
    0.39
     flatness
    0.38
    뜰
    0.38
     दुनिया
    0.38
     सामाजिक
    0.38
    POSITIVE LOGITS
     RPL
    0.46
     Invalid
    0.46
    FER
    0.44
    Renault
    0.44
     zweite
    0.44
    Vill
    0.44
    BOR
    0.43
    st
    0.43
    Second
    0.43
     postfix
    0.43
    Act Density 0.000%

    No Known Activations