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

    Neuronpedia

    INDEX
    Explanations

    trusts and estates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anol
    -0.07
     Lore
    -0.07
     ﾘ
    -0.06
     Fog
    -0.06
    (products
    -0.06
    	update
    -0.06
    .percent
    -0.06
     manifested
    -0.06
     unveiling
    -0.06
    /rc
    -0.06
    POSITIVE LOGITS
    stackoverflow
    0.07
    خانه
    0.07
    IsEmpty
    0.06
     bloc
    0.06
     insurg
    0.06
    frau
    0.06
    امت
    0.06
     svět
    0.06
    ети
    0.06
     Bols
    0.06
    Act Density 0.012%

    No Known Activations