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

    Neuronpedia

    INDEX
    Explanations

    legal compliance and regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solid
    0.32
     linear
    0.31
     in
    0.28
     an
    0.28
    0.28
     up
    0.27
     ver
    0.27
     auto
    0.27
     canceled
    0.27
     a
    0.26
    POSITIVE LOGITS
    萂
    0.34
    Faculty
    0.32
     情報
    0.32
     deputado
    0.31
    ეგისტრ
    0.30
    affichage
    0.30
     legislación
    0.30
    शांत
    0.30
     tourisme
    0.30
    舧
    0.29
    Act Density 0.008%

    No Known Activations