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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikiwa
    -0.08
    ====
    -0.08
    ooli
    -0.08
    =======
    -0.07
     журналі
    -0.07
     оператор
    -0.07
     obligaciones
    -0.07
     JMP
    -0.07
     irrev
    -0.07
    ================================================================
    -0.07
    POSITIVE LOGITS
     lag
    0.08
     б
    0.07
     titt
    0.07
     enfoque
    0.07
     b
    0.07
     HK
    0.07
     AK
    0.07
     l
    0.07
     мень
    0.07
     nouveaux
    0.07
    Act Density 0.315%

    No Known Activations