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

    Neuronpedia

    INDEX
    Explanations

    suffixes or word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilogue
    0.45
    acion
    0.41
     maturities
    0.41
     busting
    0.40
    Data
    0.40
                
    0.39
    Id
    0.39
    CriteriaUtils
    0.39
     Usuarios
    0.38
     enchantment
    0.38
    POSITIVE LOGITS
     dày
    0.40
     цієї
    0.39
    mixed
    0.39
    къ
    0.38
     redesigned
    0.38
    artige
    0.37
     aureus
    0.37
     roomy
    0.37
     nửa
    0.36
    한강
    0.36
    Act Density 0.019%

    No Known Activations