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

    Neuronpedia

    INDEX
    Explanations

    adjectival and noun-forming suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کردن
    0.65
     hard
    0.53
    ترین
    0.53
    ๑
    0.53
     دادن
    0.52
    دهای
    0.52
     keter
    0.51
     blistering
    0.51
    การ
    0.50
    вание
    0.49
    POSITIVE LOGITS
    ológica
    1.20
    ográfica
    1.20
    ométrique
    1.20
    ografico
    1.14
    ístico
    1.13
    ologique
    1.12
    ográfico
    1.11
    istico
    1.10
    ológico
    1.10
    ographique
    1.08
    Act Density 0.194%

    No Known Activations