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

    Neuronpedia

    INDEX
    Explanations

    Elizabeth and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kell
    0.43
    Kem
    0.40
    箬
    0.40
    Domin
    0.38
     dominions
    0.38
    ائِ
    0.36
    Abdul
    0.36
     Domin
    0.36
     trừ
    0.35
    Forty
    0.35
    POSITIVE LOGITS
    beth
    0.76
     Elizabethan
    0.70
     beth
    0.68
    Beth
    0.64
     Beth
    0.64
     Elizabeth
    0.62
     elizabeth
    0.56
    бет
    0.55
     beta
    0.54
    Elizabeth
    0.54
    Act Density 0.010%

    No Known Activations